[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-nes-optimizes-quadratic-bowl-via-gaussian-perturba-summary":3,"summaries-facets-categories":180,"summary-related-nes-optimizes-quadratic-bowl-via-gaussian-perturba-summary":3765},{"id":4,"title":5,"ai":6,"body":13,"categories":159,"created_at":161,"date_modified":161,"description":80,"extension":162,"faq":161,"featured":163,"kicker_label":161,"meta":164,"navigation":165,"path":166,"published_at":167,"question":161,"scraped_at":161,"seo":168,"sitemap":169,"source_id":170,"source_name":171,"source_type":172,"source_url":173,"stem":174,"tags":175,"thumbnail_url":161,"tldr":177,"tweet":161,"unknown_tags":178,"__hash__":179},"summaries\u002Fsummaries\u002Fnes-optimizes-quadratic-bowl-via-gaussian-perturba-summary.md","NES optimizes quadratic bowl via gaussian perturbations",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",8855,1292,10281,0.0019466,{"type":14,"value":15,"toc":153},"minimark",[16,21,25,63,74,90,93,97,100,115,118,122,149],[17,18,20],"h2",{"id":19},"nes-core-loop-for-black-box-optimization","NES Core Loop for Black-Box Optimization",[22,23,24],"p",{},"NES treats parameters w as mean of a fixed-variance gaussian (sigma=0.1). To maximize black-box reward f(w) without gradients:",[26,27,28,32,53,56],"ol",{},[29,30,31],"li",{},"Generate npop=50 noise samples N ~ N(0,1) (shape 50x3).",[29,33,34,35,39,40,42,43,45,46,48,49,52],{},"Perturb: w_try",[36,37,38],"span",{},"j"," = w + sigma * N",[36,41,38],{},", compute R",[36,44,38],{}," = f(w_try",[36,47,38],{},"). Here f(w) = -||w - ",[36,50,51],{},"0.5,0.1,-0.3","||^2_2 (max reward=0 at solution).",[29,54,55],{},"Standardize: A = (R - mean(R)) \u002F std(R) to zero-mean unit-variance (avoids div-by-zero on flat rewards; speeds convergence vs raw R).",[29,57,58,59,62],{},"Update: w += alpha\u002F(npop * sigma) * N.T @ A (alpha=0.001). This is score-function gradient estimator E",[36,60,61],{},"reward * noise","\u002Fsigma.",[22,64,65,66,69,70,73],{},"Starts from random w≈",[36,67,68],{},"1.76,0.40,0.98"," (reward -3.32), reaches ",[36,71,72],{},"-0.000009"," error by iter 280.",[75,76,81],"pre",{"className":77,"code":78,"language":79,"meta":80,"style":80},"language-python shiki shiki-themes github-light github-dark","w = w + alpha\u002F(npop*sigma) * np.dot(N.T, A)\n","python","",[82,83,84],"code",{"__ignoreMap":80},[36,85,88],{"class":86,"line":87},"line",1,[36,89,78],{},[22,91,92],{},"sigma scales perturbation size and normalizes estimator (divisor matches multiplier for consistent gradient scale).",[17,94,96],{"id":95},"proven-convergence-on-toy-quadratic","Proven Convergence on Toy Quadratic",[22,98,99],{},"300 iters suffice; prints every 20 show steady progress:",[101,102,103,106,109,112],"ul",{},[29,104,105],{},"Iter 0: reward -3.323",[29,107,108],{},"Iter 100: -0.727",[29,110,111],{},"Iter 200: -0.001",[29,113,114],{},"Iter 280: -0.000009",[22,116,117],{},"Toy mimics NN optimization: f(w) would forward NN on env, return total reward. Solution hidden from optimizer.",[17,119,121],{"id":120},"insights-from-implementers","Insights from Implementers",[101,123,124,131,137,143],{},[29,125,126,130],{},[127,128,129],"strong",{},"Standardization optional but boosts speed",": Raw R works (paper-equivalent via Section 3.2), but centering\u002Fscaling prevents stagnation on negative\u002Fflat rewards.",[29,132,133,136],{},[127,134,135],{},"Edge cases",": Add epsilon to std(R) avoids div0 when all R equal (common early\u002Fsimple problems).",[29,138,139,142],{},[127,140,141],{},"Extensions",": Handles moving targets with small jitters; libs like evostra apply to Flappy Bird. No crossover needed vs GA—NES is gradient-like via log-prob derivative.",[29,144,145,148],{},[127,146,147],{},"Deployment",": Save final w; reconstruct NN. Practical for RL vs DQN (no backprop, parallelizable evals).",[150,151,152],"style",{},"html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":80,"searchDepth":154,"depth":154,"links":155},2,[156,157,158],{"id":19,"depth":154,"text":20},{"id":95,"depth":154,"text":96},{"id":120,"depth":154,"text":121},[160],"Data Science & Visualization",null,"md",false,{},true,"\u002Fsummaries\u002Fnes-optimizes-quadratic-bowl-via-gaussian-perturba-summary","2026-04-08 21:21:20",{"title":5,"description":80},{"loc":166},"24c62cc73ee60bc6","Andrej Karpathy Gists","article","https:\u002F\u002Funknown","summaries\u002Fnes-optimizes-quadratic-bowl-via-gaussian-perturba-summary",[79,176],"machine-learning","Sample 50 perturbed weights from N(w, 0.1), weight by standardized rewards, update w by 0.001\u002F(50*0.1) * sum(noise * weights) to converge in 300 iters.",[],"THgP6_hPLQzW9Arl2BqfDCHYij8HS6-ncC3XkmeXu-Y",[181,184,187,190,193,196,198,200,202,204,206,208,211,213,215,217,219,221,223,225,227,229,232,234,236,238,241,243,245,248,250,252,254,256,258,260,262,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753,755,757,759,761,763,765,767,769,771,773,775,777,779,781,783,785,787,789,791,793,795,797,799,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991,993,995,997,999,1001,1003,1005,1007,1009,1011,1013,1015,1017,1019,1021,1023,1025,1027,1029,1031,1033,1035,1037,1039,1041,1043,1045,1047,1049,1051,1053,1055,1057,1059,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1097,1099,1101,1103,1105,1107,1109,1111,1113,1115,1117,1119,1121,1123,1125,1127,1129,1131,1133,1135,1137,1139,1141,1143,1145,1147,1149,1151,1153,1155,1157,1159,1161,1163,1165,1167,1169,1171,1173,1175,1177,1179,1181,1183,1185,1187,1189,1191,1193,1195,1197,1199,1201,1203,1205,1207,1209,1211,1213,1215,1217,1219,1221,1223,1225,1227,1229,1231,1233,1235,1237,1239,1241,1243,1245,1247,1249,1251,1253,1255,1257,1259,1261,1263,1265,1267,1269,1271,1273,1275,1277,1279,1281,1283,1285,1287,1289,1291,1293,1295,1297,1299,1301,1303,1305,1307,1309,1311,1313,1315,1317,1319,1321,1323,1325,1327,1329,1331,1333,1335,1337,1339,1341,1343,1345,1347,1349,1351,1353,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1401,1403,1405,1407,1409,1411,1413,1415,1417,1419,1421,1423,1425,1427,1429,1431,1433,1435,1437,1439,1441,1443,1445,1447,1449,1451,1453,1455,1457,1459,1461,1463,1465,1467,1469,1471,1473,1475,1477,1479,1481,1483,1485,1487,1489,1491,1493,1495,1497,1499,1501,1503,1505,1507,1509,1511,1513,1515,1517,1519,1521,1523,1525,1527,1529,1531,1533,1535,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1593,1595,1597,1599,1601,1603,1605,1607,1609,1611,1613,1615,1617,1619,1621,1623,1625,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697,1699,1701,1703,1705,1707,1709,1711,1713,1715,1717,1719,1721,1723,1725,1727,1729,1731,1733,1735,1737,1739,1741,1743,1745,1747,1749,1751,1753,1755,1757,1759,1761,1763,1765,1767,1769,1771,1773,1775,1777,1779,1781,1783,1785,1787,1789,1791,1793,1795,1797,1799,1801,1803,1805,1807,1809,1811,1813,1815,1817,1819,1821,1823,1825,1827,1829,1831,1833,1835,1837,1839,1841,1843,1845,1847,1849,1851,1853,1855,1857,1859,1861,1863,1865,1867,1869,1871,1873,1875,1877,1879,1881,1883,1885,1887,1889,1891,1893,1895,1897,1899,1901,1903,1905,1907,1909,1911,1913,1915,1917,1919,1921,1923,1925,1927,1929,1931,1933,1935,1937,1939,1941,1943,1945,1947,1949,1951,1953,1955,1957,1959,1961,1963,1965,1967,1969,1971,1973,1975,1977,1979,1981,1983,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2045,2047,2049,2051,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071,2073,2075,2077,2079,2081,2083,2085,2087,2089,2091,2093,2095,2097,2099,2101,2103,2105,2107,2109,2111,2113,2115,2117,2119,2121,2123,2125,2127,2129,2131,2133,2135,2137,2139,2141,2143,2145,2147,2149,2151,2153,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2195,2197,2199,2201,2203,2205,2207,2209,2211,2213,2215,2217,2219,2221,2223,2225,2227,2229,2231,2233,2235,2237,2239,2241,2243,2245,2247,2249,2251,2253,2255,2257,2259,2261,2263,2265,2267,2269,2271,2273,2275,2277,2279,2281,2283,2285,2287,2289,2291,2293,2295,2297,2299,2301,2303,2305,2307,2309,2311,2313,2315,2317,2319,2321,2323,2325,2327,2329,2331,2333,2335,2337,2339,2341,2343,2345,2347,2349,2351,2353,2355,2357,2359,2361,2363,2365,2367,2369,2371,2373,2375,2377,2379,2381,2383,2385,2387,2389,2391,2393,2395,2397,2399,2401,2403,2405,2407,2409,2411,2413,2415,2417,2419,2421,2423,2425,2427,2429,2431,2433,2435,2437,2439,2441,2443,2445,2447,2449,2451,2453,2455,2457,2459,2461,2463,2465,2467,2469,2471,2473,2475,2477,2479,2481,2483,2485,2487,2489,2491,2493,2495,2497,2499,2501,2503,2505,2507,2509,2511,2513,2515,2517,2519,2521,2523,2525,2527,2529,2531,2533,2535,2537,2539,2541,2543,2545,2547,2549,2551,2553,2555,2557,2559,2561,2563,2565,2567,2569,2571,2573,2575,2577,2579,2581,2583,2585,2587,2589,2591,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613,2615,2617,2619,2621,2623,2625,2627,2629,2631,2633,2635,2637,2639,2641,2643,2645,2647,2649,2651,2653,2655,2657,2659,2661,2663,2665,2667,2669,2671,2673,2675,2677,2679,2681,2683,2685,2687,2689,2691,2693,2695,2697,2699,2701,2703,2705,2707,2709,2711,2713,2715,2717,2719,2721,2723,2725,2727,2729,2731,2733,2735,2737,2739,2741,2743,2745,2747,2749,2751,2753,2755,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2859,2861,2863,2865,2867,2869,2871,2873,2875,2877,2879,2881,2883,2885,2887,2889,2891,2893,2895,2897,2899,2901,2903,2905,2907,2909,2911,2913,2915,2917,2919,2921,2923,2925,2927,2929,2931,2933,2935,2937,2939,2941,2943,2945,2947,2949,2951,2953,2955,2957,2959,2961,2963,2965,2967,2969,2971,2973,2975,2977,2979,2981,2983,2985,2987,2989,2991,2993,2995,2997,2999,3001,3003,3005,3007,3009,3011,3013,3015,3017,3019,3021,3023,3025,3027,3029,3031,3033,3035,3037,3039,3041,3043,3045,3047,3049,3051,3053,3055,3057,3059,3061,3063,3065,3067,3069,3071,3073,3075,3077,3079,3081,3083,3085,3087,3089,3091,3093,3095,3097,3099,3101,3103,3105,3107,3109,3111,3113,3115,3117,3119,3121,3123,3125,3127,3129,3131,3133,3135,3137,3139,3141,3143,3145,3147,3149,3151,3153,3155,3157,3159,3161,3163,3165,3167,3169,3171,3173,3175,3177,3179,3181,3183,3185,3187,3189,3191,3193,3195,3197,3199,3201,3203,3205,3207,3209,3211,3213,3215,3217,3219,3221,3223,3225,3227,3229,3231,3233,3235,3237,3239,3241,3243,3245,3247,3249,3251,3253,3255,3257,3259,3261,3263,3265,3267,3269,3271,3273,3275,3277,3279,3281,3283,3285,3287,3289,3291,3293,3295,3297,3299,3301,3303,3305,3307,3309,3311,3313,3315,3317,3319,3321,3323,3325,3327,3329,3331,3333,3335,3337,3339,3341,3343,3345,3347,3349,3351,3353,3355,3357,3359,3361,3363,3365,3367,3369,3371,3373,3375,3377,3379,3381,3383,3385,3387,3389,3391,3393,3395,3397,3399,3401,3403,3405,3407,3409,3411,3413,3415,3417,3419,3421,3423,3425,3427,3429,3431,3433,3435,3437,3439,3441,3443,3445,3447,3449,3451,3453,3455,3457,3459,3461,3463,3465,3467,3469,3471,3473,3475,3477,3479,3481,3483,3485,3487,3489,3491,3493,3495,3497,3499,3501,3503,3505,3507,3509,3511,3513,3515,3517,3519,3521,3523,3525,3527,3529,3531,3533,3535,3537,3539,3541,3543,3545,3547,3549,3551,3553,3555,3557,3559,3561,3563,3565,3567,3569,3571,3573,3575,3577,3579,3581,3583,3585,3587,3589,3591,3593,3595,3597,3599,3601,3603,3605,3607,3609,3611,3613,3615,3617,3619,3621,3623,3625,3627,3629,3631,3633,3635,3637,3639,3641,3643,3645,3647,3649,3651,3653,3655,3657,3659,3661,3663,3665,3667,3669,3671,3673,3675,3677,3679,3681,3683,3685,3687,3689,3691,3693,3695,3697,3699,3701,3703,3705,3707,3709,3711,3713,3715,3717,3719,3721,3723,3725,3727,3729,3731,3733,3735,3737,3739,3741,3743,3745,3747,3749,3751,3753,3755,3757,3759,3761,3763],{"categories":182},[183],"Developer Productivity",{"categories":185},[186],"Business & SaaS",{"categories":188},[189],"AI & LLMs",{"categories":191},[192],"AI Automation",{"categories":194},[195],"Product Strategy",{"categories":197},[189],{"categories":199},[183],{"categories":201},[186],{"categories":203},[],{"categories":205},[189],{"categories":207},[],{"categories":209},[210],"AI News & Trends",{"categories":212},[192],{"categories":214},[210],{"categories":216},[192],{"categories":218},[192],{"categories":220},[189],{"categories":222},[189],{"categories":224},[210],{"categories":226},[189],{"categories":228},[],{"categories":230},[231],"Design & Frontend",{"categories":233},[160],{"categories":235},[210],{"categories":237},[],{"categories":239},[240],"Software Engineering",{"categories":242},[189],{"categories":244},[192],{"categories":246},[247],"Marketing & Growth",{"categories":249},[189],{"categories":251},[192],{"categories":253},[],{"categories":255},[],{"categories":257},[231],{"categories":259},[192],{"categories":261},[183],{"categories":263},[231],{"categories":265},[189],{"categories":267},[192],{"categories":269},[210],{"categories":271},[],{"categories":273},[],{"categories":275},[192],{"categories":277},[240],{"categories":279},[],{"categories":281},[186],{"categories":283},[],{"categories":285},[],{"categories":287},[192],{"categories":289},[192],{"categories":291},[189],{"categories":293},[],{"categories":295},[240],{"categories":297},[],{"categories":299},[],{"categories":301},[],{"categories":303},[189],{"categories":305},[247],{"categories":307},[231],{"categories":309},[231],{"categories":311},[189],{"categories":313},[192],{"categories":315},[189],{"categories":317},[189],{"categories":319},[192],{"categories":321},[192],{"categories":323},[160],{"categories":325},[210],{"categories":327},[192],{"categories":329},[247],{"categories":331},[192],{"categories":333},[195],{"categories":335},[],{"categories":337},[192],{"categories":339},[],{"categories":341},[192],{"categories":343},[240],{"categories":345},[231],{"categories":347},[189],{"categories":349},[],{"categories":351},[],{"categories":353},[192],{"categories":355},[],{"categories":357},[189],{"categories":359},[],{"categories":361},[183],{"categories":363},[240],{"categories":365},[186],{"categories":367},[210],{"categories":369},[189],{"categories":371},[],{"categories":373},[189],{"categories":375},[],{"categories":377},[240],{"categories":379},[160],{"categories":381},[],{"categories":383},[189],{"categories":385},[231],{"categories":387},[],{"categories":389},[231],{"categories":391},[192],{"categories":393},[],{"categories":395},[192],{"categories":397},[210],{"categories":399},[186],{"categories":401},[189],{"categories":403},[],{"categories":405},[192],{"categories":407},[189],{"categories":409},[195],{"categories":411},[],{"categories":413},[189],{"categories":415},[192],{"categories":417},[192],{"categories":419},[],{"categories":421},[160],{"categories":423},[189],{"categories":425},[],{"categories":427},[183],{"categories":429},[186],{"categories":431},[189],{"categories":433},[192],{"categories":435},[240],{"categories":437},[189],{"categories":439},[],{"categories":441},[],{"categories":443},[189],{"categories":445},[],{"categories":447},[231],{"categories":449},[],{"categories":451},[189],{"categories":453},[],{"categories":455},[192],{"categories":457},[189],{"categories":459},[231],{"categories":461},[],{"categories":463},[189],{"categories":465},[189],{"categories":467},[186],{"categories":469},[192],{"categories":471},[189],{"categories":473},[231],{"categories":475},[192],{"categories":477},[],{"categories":479},[],{"categories":481},[210],{"categories":483},[],{"categories":485},[189],{"categories":487},[186,247],{"categories":489},[],{"categories":491},[189],{"categories":493},[],{"categories":495},[],{"categories":497},[189],{"categories":499},[],{"categories":501},[189],{"categories":503},[504],"DevOps & Cloud",{"categories":506},[],{"categories":508},[210],{"categories":510},[231],{"categories":512},[],{"categories":514},[210],{"categories":516},[210],{"categories":518},[189],{"categories":520},[247],{"categories":522},[],{"categories":524},[186],{"categories":526},[],{"categories":528},[189,504],{"categories":530},[189],{"categories":532},[189],{"categories":534},[192],{"categories":536},[189,240],{"categories":538},[160],{"categories":540},[189],{"categories":542},[247],{"categories":544},[192],{"categories":546},[192],{"categories":548},[],{"categories":550},[192],{"categories":552},[189,186],{"categories":554},[],{"categories":556},[231],{"categories":558},[231],{"categories":560},[],{"categories":562},[],{"categories":564},[210],{"categories":566},[],{"categories":568},[183],{"categories":570},[240],{"categories":572},[189],{"categories":574},[231],{"categories":576},[192],{"categories":578},[240],{"categories":580},[210],{"categories":582},[231],{"categories":584},[],{"categories":586},[189],{"categories":588},[189],{"categories":590},[189],{"categories":592},[210],{"categories":594},[183],{"categories":596},[189],{"categories":598},[192],{"categories":600},[504],{"categories":602},[231],{"categories":604},[192],{"categories":606},[],{"categories":608},[],{"categories":610},[231],{"categories":612},[210],{"categories":614},[160],{"categories":616},[],{"categories":618},[189],{"categories":620},[189],{"categories":622},[186],{"categories":624},[189],{"categories":626},[189],{"categories":628},[210],{"categories":630},[],{"categories":632},[192],{"categories":634},[240],{"categories":636},[],{"categories":638},[189],{"categories":640},[189],{"categories":642},[192],{"categories":644},[],{"categories":646},[],{"categories":648},[189],{"categories":650},[],{"categories":652},[186],{"categories":654},[192],{"categories":656},[],{"categories":658},[183],{"categories":660},[189],{"categories":662},[186],{"categories":664},[210],{"categories":666},[],{"categories":668},[],{"categories":670},[],{"categories":672},[210],{"categories":674},[210],{"categories":676},[],{"categories":678},[],{"categories":680},[186],{"categories":682},[],{"categories":684},[],{"categories":686},[183],{"categories":688},[],{"categories":690},[247],{"categories":692},[192],{"categories":694},[186],{"categories":696},[192],{"categories":698},[240],{"categories":700},[],{"categories":702},[195],{"categories":704},[231],{"categories":706},[240],{"categories":708},[189],{"categories":710},[192],{"categories":712},[186],{"categories":714},[189],{"categories":716},[],{"categories":718},[],{"categories":720},[240],{"categories":722},[160],{"categories":724},[195],{"categories":726},[192],{"categories":728},[189],{"categories":730},[],{"categories":732},[504],{"categories":734},[],{"categories":736},[192],{"categories":738},[],{"categories":740},[],{"categories":742},[189],{"categories":744},[231],{"categories":746},[247],{"categories":748},[192],{"categories":750},[],{"categories":752},[183],{"categories":754},[],{"categories":756},[210],{"categories":758},[189,504],{"categories":760},[210],{"categories":762},[189],{"categories":764},[186],{"categories":766},[189],{"categories":768},[],{"categories":770},[186],{"categories":772},[],{"categories":774},[240],{"categories":776},[231],{"categories":778},[210],{"categories":780},[160],{"categories":782},[183],{"categories":784},[189],{"categories":786},[240],{"categories":788},[],{"categories":790},[],{"categories":792},[195],{"categories":794},[],{"categories":796},[189],{"categories":798},[],{"categories":800},[231],{"categories":802},[231],{"categories":804},[231],{"categories":806},[],{"categories":808},[],{"categories":810},[210],{"categories":812},[192],{"categories":814},[189],{"categories":816},[189],{"categories":818},[189],{"categories":820},[186],{"categories":822},[189],{"categories":824},[],{"categories":826},[240],{"categories":828},[240],{"categories":830},[186],{"categories":832},[],{"categories":834},[189],{"categories":836},[189],{"categories":838},[186],{"categories":840},[210],{"categories":842},[247],{"categories":844},[192],{"categories":846},[],{"categories":848},[231],{"categories":850},[],{"categories":852},[189],{"categories":854},[],{"categories":856},[186],{"categories":858},[192],{"categories":860},[],{"categories":862},[504],{"categories":864},[160],{"categories":866},[240],{"categories":868},[247],{"categories":870},[240],{"categories":872},[192],{"categories":874},[],{"categories":876},[],{"categories":878},[192],{"categories":880},[183],{"categories":882},[192],{"categories":884},[195],{"categories":886},[186],{"categories":888},[],{"categories":890},[189],{"categories":892},[195],{"categories":894},[189],{"categories":896},[189],{"categories":898},[247],{"categories":900},[231],{"categories":902},[192],{"categories":904},[],{"categories":906},[],{"categories":908},[504],{"categories":910},[240],{"categories":912},[],{"categories":914},[192],{"categories":916},[189],{"categories":918},[231,189],{"categories":920},[183],{"categories":922},[],{"categories":924},[189],{"categories":926},[183],{"categories":928},[231],{"categories":930},[192],{"categories":932},[240],{"categories":934},[],{"categories":936},[189],{"categories":938},[],{"categories":940},[183],{"categories":942},[],{"categories":944},[192],{"categories":946},[195],{"categories":948},[189],{"categories":950},[189],{"categories":952},[231],{"categories":954},[192],{"categories":956},[504],{"categories":958},[231],{"categories":960},[192],{"categories":962},[189],{"categories":964},[189],{"categories":966},[189],{"categories":968},[210],{"categories":970},[],{"categories":972},[195],{"categories":974},[192],{"categories":976},[231],{"categories":978},[192],{"categories":980},[240],{"categories":982},[231],{"categories":984},[192],{"categories":986},[210],{"categories":988},[],{"categories":990},[189],{"categories":992},[231],{"categories":994},[189],{"categories":996},[183],{"categories":998},[210],{"categories":1000},[189],{"categories":1002},[247],{"categories":1004},[189],{"categories":1006},[189],{"categories":1008},[192],{"categories":1010},[192],{"categories":1012},[189],{"categories":1014},[192],{"categories":1016},[231],{"categories":1018},[189],{"categories":1020},[],{"categories":1022},[],{"categories":1024},[240],{"categories":1026},[],{"categories":1028},[183],{"categories":1030},[504],{"categories":1032},[],{"categories":1034},[183],{"categories":1036},[186],{"categories":1038},[247],{"categories":1040},[],{"categories":1042},[186],{"categories":1044},[],{"categories":1046},[],{"categories":1048},[],{"categories":1050},[],{"categories":1052},[],{"categories":1054},[189],{"categories":1056},[192],{"categories":1058},[504],{"categories":1060},[183],{"categories":1062},[189],{"categories":1064},[240],{"categories":1066},[195],{"categories":1068},[189],{"categories":1070},[247],{"categories":1072},[189],{"categories":1074},[189],{"categories":1076},[189],{"categories":1078},[189,183],{"categories":1080},[240],{"categories":1082},[240],{"categories":1084},[231],{"categories":1086},[189],{"categories":1088},[],{"categories":1090},[],{"categories":1092},[],{"categories":1094},[240],{"categories":1096},[160],{"categories":1098},[210],{"categories":1100},[231],{"categories":1102},[],{"categories":1104},[189],{"categories":1106},[189],{"categories":1108},[],{"categories":1110},[],{"categories":1112},[192],{"categories":1114},[189],{"categories":1116},[186],{"categories":1118},[],{"categories":1120},[183],{"categories":1122},[189],{"categories":1124},[183],{"categories":1126},[189],{"categories":1128},[240],{"categories":1130},[247],{"categories":1132},[189,231],{"categories":1134},[210],{"categories":1136},[231],{"categories":1138},[],{"categories":1140},[504],{"categories":1142},[231],{"categories":1144},[192],{"categories":1146},[],{"categories":1148},[],{"categories":1150},[],{"categories":1152},[],{"categories":1154},[240],{"categories":1156},[192],{"categories":1158},[192],{"categories":1160},[504],{"categories":1162},[189],{"categories":1164},[189],{"categories":1166},[189],{"categories":1168},[],{"categories":1170},[231],{"categories":1172},[],{"categories":1174},[],{"categories":1176},[192],{"categories":1178},[],{"categories":1180},[],{"categories":1182},[247],{"categories":1184},[247],{"categories":1186},[192],{"categories":1188},[],{"categories":1190},[189],{"categories":1192},[189],{"categories":1194},[240],{"categories":1196},[231],{"categories":1198},[231],{"categories":1200},[192],{"categories":1202},[183],{"categories":1204},[189],{"categories":1206},[231],{"categories":1208},[231],{"categories":1210},[192],{"categories":1212},[192],{"categories":1214},[189],{"categories":1216},[],{"categories":1218},[],{"categories":1220},[189],{"categories":1222},[192],{"categories":1224},[210],{"categories":1226},[240],{"categories":1228},[183],{"categories":1230},[189],{"categories":1232},[],{"categories":1234},[192],{"categories":1236},[192],{"categories":1238},[],{"categories":1240},[183],{"categories":1242},[189],{"categories":1244},[183],{"categories":1246},[183],{"categories":1248},[],{"categories":1250},[],{"categories":1252},[192],{"categories":1254},[192],{"categories":1256},[189],{"categories":1258},[189],{"categories":1260},[210],{"categories":1262},[160],{"categories":1264},[195],{"categories":1266},[210],{"categories":1268},[231],{"categories":1270},[],{"categories":1272},[210],{"categories":1274},[],{"categories":1276},[],{"categories":1278},[],{"categories":1280},[],{"categories":1282},[240],{"categories":1284},[160],{"categories":1286},[],{"categories":1288},[189],{"categories":1290},[189],{"categories":1292},[160],{"categories":1294},[240],{"categories":1296},[],{"categories":1298},[],{"categories":1300},[192],{"categories":1302},[210],{"categories":1304},[210],{"categories":1306},[192],{"categories":1308},[183],{"categories":1310},[189,504],{"categories":1312},[],{"categories":1314},[231],{"categories":1316},[183],{"categories":1318},[192],{"categories":1320},[231],{"categories":1322},[],{"categories":1324},[192],{"categories":1326},[192],{"categories":1328},[189],{"categories":1330},[247],{"categories":1332},[240],{"categories":1334},[231],{"categories":1336},[],{"categories":1338},[192],{"categories":1340},[189],{"categories":1342},[192],{"categories":1344},[192],{"categories":1346},[192],{"categories":1348},[247],{"categories":1350},[192],{"categories":1352},[189],{"categories":1354},[],{"categories":1356},[247],{"categories":1358},[210],{"categories":1360},[192],{"categories":1362},[],{"categories":1364},[],{"categories":1366},[189],{"categories":1368},[192],{"categories":1370},[210],{"categories":1372},[192],{"categories":1374},[],{"categories":1376},[],{"categories":1378},[],{"categories":1380},[192],{"categories":1382},[],{"categories":1384},[],{"categories":1386},[160],{"categories":1388},[189],{"categories":1390},[160],{"categories":1392},[210],{"categories":1394},[189],{"categories":1396},[189],{"categories":1398},[192],{"categories":1400},[189],{"categories":1402},[],{"categories":1404},[],{"categories":1406},[504],{"categories":1408},[],{"categories":1410},[],{"categories":1412},[183],{"categories":1414},[],{"categories":1416},[],{"categories":1418},[],{"categories":1420},[],{"categories":1422},[240],{"categories":1424},[210],{"categories":1426},[247],{"categories":1428},[186],{"categories":1430},[189],{"categories":1432},[189],{"categories":1434},[186],{"categories":1436},[],{"categories":1438},[231],{"categories":1440},[192],{"categories":1442},[186],{"categories":1444},[189],{"categories":1446},[189],{"categories":1448},[183],{"categories":1450},[],{"categories":1452},[183],{"categories":1454},[189],{"categories":1456},[247],{"categories":1458},[192],{"categories":1460},[210],{"categories":1462},[186],{"categories":1464},[189],{"categories":1466},[192],{"categories":1468},[],{"categories":1470},[189],{"categories":1472},[183],{"categories":1474},[189],{"categories":1476},[],{"categories":1478},[210],{"categories":1480},[189],{"categories":1482},[],{"categories":1484},[186],{"categories":1486},[189],{"categories":1488},[],{"categories":1490},[],{"categories":1492},[],{"categories":1494},[189],{"categories":1496},[],{"categories":1498},[504],{"categories":1500},[189],{"categories":1502},[],{"categories":1504},[189],{"categories":1506},[189],{"categories":1508},[189],{"categories":1510},[189,504],{"categories":1512},[189],{"categories":1514},[189],{"categories":1516},[231],{"categories":1518},[192],{"categories":1520},[],{"categories":1522},[192],{"categories":1524},[189],{"categories":1526},[189],{"categories":1528},[189],{"categories":1530},[183],{"categories":1532},[183],{"categories":1534},[240],{"categories":1536},[231],{"categories":1538},[192],{"categories":1540},[],{"categories":1542},[189],{"categories":1544},[210],{"categories":1546},[189],{"categories":1548},[186],{"categories":1550},[],{"categories":1552},[504],{"categories":1554},[231],{"categories":1556},[231],{"categories":1558},[192],{"categories":1560},[210],{"categories":1562},[192],{"categories":1564},[189],{"categories":1566},[],{"categories":1568},[189],{"categories":1570},[],{"categories":1572},[],{"categories":1574},[189],{"categories":1576},[189],{"categories":1578},[189],{"categories":1580},[192],{"categories":1582},[189],{"categories":1584},[],{"categories":1586},[160],{"categories":1588},[192],{"categories":1590},[],{"categories":1592},[],{"categories":1594},[189],{"categories":1596},[210],{"categories":1598},[],{"categories":1600},[231],{"categories":1602},[504],{"categories":1604},[210],{"categories":1606},[240],{"categories":1608},[240],{"categories":1610},[210],{"categories":1612},[210],{"categories":1614},[504],{"categories":1616},[],{"categories":1618},[210],{"categories":1620},[189],{"categories":1622},[183],{"categories":1624},[210],{"categories":1626},[],{"categories":1628},[160],{"categories":1630},[210],{"categories":1632},[240],{"categories":1634},[210],{"categories":1636},[504],{"categories":1638},[189],{"categories":1640},[189],{"categories":1642},[],{"categories":1644},[186],{"categories":1646},[],{"categories":1648},[],{"categories":1650},[189],{"categories":1652},[189],{"categories":1654},[189],{"categories":1656},[189],{"categories":1658},[],{"categories":1660},[160],{"categories":1662},[183],{"categories":1664},[],{"categories":1666},[189],{"categories":1668},[189],{"categories":1670},[504],{"categories":1672},[504],{"categories":1674},[],{"categories":1676},[192],{"categories":1678},[210],{"categories":1680},[210],{"categories":1682},[189],{"categories":1684},[192],{"categories":1686},[],{"categories":1688},[231],{"categories":1690},[189],{"categories":1692},[189],{"categories":1694},[],{"categories":1696},[],{"categories":1698},[504],{"categories":1700},[189],{"categories":1702},[240],{"categories":1704},[186],{"categories":1706},[189],{"categories":1708},[],{"categories":1710},[192],{"categories":1712},[183],{"categories":1714},[183],{"categories":1716},[],{"categories":1718},[189],{"categories":1720},[231],{"categories":1722},[192],{"categories":1724},[],{"categories":1726},[189],{"categories":1728},[189],{"categories":1730},[192],{"categories":1732},[],{"categories":1734},[192],{"categories":1736},[240],{"categories":1738},[],{"categories":1740},[189],{"categories":1742},[],{"categories":1744},[189],{"categories":1746},[],{"categories":1748},[189],{"categories":1750},[189],{"categories":1752},[],{"categories":1754},[189],{"categories":1756},[210],{"categories":1758},[189],{"categories":1760},[189],{"categories":1762},[183],{"categories":1764},[189],{"categories":1766},[210],{"categories":1768},[192],{"categories":1770},[],{"categories":1772},[189],{"categories":1774},[247],{"categories":1776},[],{"categories":1778},[],{"categories":1780},[],{"categories":1782},[183],{"categories":1784},[210],{"categories":1786},[192],{"categories":1788},[189],{"categories":1790},[231],{"categories":1792},[192],{"categories":1794},[],{"categories":1796},[192],{"categories":1798},[],{"categories":1800},[189],{"categories":1802},[192],{"categories":1804},[189],{"categories":1806},[],{"categories":1808},[189],{"categories":1810},[189],{"categories":1812},[210],{"categories":1814},[231],{"categories":1816},[192],{"categories":1818},[231],{"categories":1820},[186],{"categories":1822},[],{"categories":1824},[],{"categories":1826},[189],{"categories":1828},[183],{"categories":1830},[210],{"categories":1832},[],{"categories":1834},[],{"categories":1836},[240],{"categories":1838},[231],{"categories":1840},[],{"categories":1842},[189],{"categories":1844},[],{"categories":1846},[247],{"categories":1848},[189],{"categories":1850},[504],{"categories":1852},[240],{"categories":1854},[],{"categories":1856},[192],{"categories":1858},[189],{"categories":1860},[192],{"categories":1862},[192],{"categories":1864},[189],{"categories":1866},[],{"categories":1868},[183],{"categories":1870},[189],{"categories":1872},[186],{"categories":1874},[240],{"categories":1876},[231],{"categories":1878},[],{"categories":1880},[],{"categories":1882},[],{"categories":1884},[192],{"categories":1886},[231],{"categories":1888},[210],{"categories":1890},[189],{"categories":1892},[210],{"categories":1894},[231],{"categories":1896},[],{"categories":1898},[231],{"categories":1900},[210],{"categories":1902},[186],{"categories":1904},[189],{"categories":1906},[210],{"categories":1908},[247],{"categories":1910},[],{"categories":1912},[],{"categories":1914},[160],{"categories":1916},[189,240],{"categories":1918},[210],{"categories":1920},[189],{"categories":1922},[192],{"categories":1924},[192],{"categories":1926},[189],{"categories":1928},[],{"categories":1930},[240],{"categories":1932},[189],{"categories":1934},[160],{"categories":1936},[192],{"categories":1938},[247],{"categories":1940},[504],{"categories":1942},[],{"categories":1944},[183],{"categories":1946},[192],{"categories":1948},[192],{"categories":1950},[240],{"categories":1952},[189],{"categories":1954},[189],{"categories":1956},[],{"categories":1958},[],{"categories":1960},[],{"categories":1962},[504],{"categories":1964},[210],{"categories":1966},[189],{"categories":1968},[189],{"categories":1970},[189],{"categories":1972},[],{"categories":1974},[160],{"categories":1976},[186],{"categories":1978},[],{"categories":1980},[192],{"categories":1982},[504],{"categories":1984},[],{"categories":1986},[231],{"categories":1988},[231],{"categories":1990},[],{"categories":1992},[240],{"categories":1994},[231],{"categories":1996},[189],{"categories":1998},[],{"categories":2000},[210],{"categories":2002},[189],{"categories":2004},[231],{"categories":2006},[192],{"categories":2008},[210],{"categories":2010},[],{"categories":2012},[192],{"categories":2014},[231],{"categories":2016},[189],{"categories":2018},[],{"categories":2020},[189],{"categories":2022},[189],{"categories":2024},[504],{"categories":2026},[210],{"categories":2028},[160],{"categories":2030},[160],{"categories":2032},[],{"categories":2034},[],{"categories":2036},[],{"categories":2038},[192],{"categories":2040},[240],{"categories":2042},[240],{"categories":2044},[],{"categories":2046},[],{"categories":2048},[189],{"categories":2050},[],{"categories":2052},[192],{"categories":2054},[189],{"categories":2056},[],{"categories":2058},[189],{"categories":2060},[186],{"categories":2062},[189],{"categories":2064},[247],{"categories":2066},[192],{"categories":2068},[189],{"categories":2070},[240],{"categories":2072},[210],{"categories":2074},[192],{"categories":2076},[],{"categories":2078},[210],{"categories":2080},[192],{"categories":2082},[192],{"categories":2084},[],{"categories":2086},[186],{"categories":2088},[192],{"categories":2090},[],{"categories":2092},[189],{"categories":2094},[183],{"categories":2096},[210],{"categories":2098},[504],{"categories":2100},[192],{"categories":2102},[192],{"categories":2104},[183],{"categories":2106},[189],{"categories":2108},[],{"categories":2110},[],{"categories":2112},[231],{"categories":2114},[189,186],{"categories":2116},[],{"categories":2118},[183],{"categories":2120},[160],{"categories":2122},[189],{"categories":2124},[240],{"categories":2126},[189],{"categories":2128},[192],{"categories":2130},[189],{"categories":2132},[189],{"categories":2134},[210],{"categories":2136},[192],{"categories":2138},[],{"categories":2140},[],{"categories":2142},[192],{"categories":2144},[189],{"categories":2146},[504],{"categories":2148},[],{"categories":2150},[189],{"categories":2152},[192],{"categories":2154},[],{"categories":2156},[189],{"categories":2158},[247],{"categories":2160},[160],{"categories":2162},[192],{"categories":2164},[189],{"categories":2166},[504],{"categories":2168},[],{"categories":2170},[189],{"categories":2172},[247],{"categories":2174},[231],{"categories":2176},[189],{"categories":2178},[],{"categories":2180},[247],{"categories":2182},[210],{"categories":2184},[189],{"categories":2186},[189],{"categories":2188},[183],{"categories":2190},[],{"categories":2192},[],{"categories":2194},[231],{"categories":2196},[189],{"categories":2198},[160],{"categories":2200},[247],{"categories":2202},[247],{"categories":2204},[210],{"categories":2206},[],{"categories":2208},[],{"categories":2210},[189],{"categories":2212},[],{"categories":2214},[189,240],{"categories":2216},[210],{"categories":2218},[192],{"categories":2220},[240],{"categories":2222},[189],{"categories":2224},[183],{"categories":2226},[],{"categories":2228},[],{"categories":2230},[183],{"categories":2232},[247],{"categories":2234},[189],{"categories":2236},[],{"categories":2238},[231,189],{"categories":2240},[504],{"categories":2242},[183],{"categories":2244},[],{"categories":2246},[186],{"categories":2248},[186],{"categories":2250},[189],{"categories":2252},[240],{"categories":2254},[192],{"categories":2256},[210],{"categories":2258},[247],{"categories":2260},[231],{"categories":2262},[189],{"categories":2264},[189],{"categories":2266},[189],{"categories":2268},[183],{"categories":2270},[189],{"categories":2272},[192],{"categories":2274},[210],{"categories":2276},[],{"categories":2278},[],{"categories":2280},[160],{"categories":2282},[240],{"categories":2284},[189],{"categories":2286},[231],{"categories":2288},[160],{"categories":2290},[189],{"categories":2292},[189],{"categories":2294},[192],{"categories":2296},[192],{"categories":2298},[189,186],{"categories":2300},[],{"categories":2302},[231],{"categories":2304},[],{"categories":2306},[189],{"categories":2308},[210],{"categories":2310},[183],{"categories":2312},[183],{"categories":2314},[192],{"categories":2316},[189],{"categories":2318},[186],{"categories":2320},[240],{"categories":2322},[247],{"categories":2324},[],{"categories":2326},[210],{"categories":2328},[189],{"categories":2330},[189],{"categories":2332},[210],{"categories":2334},[240],{"categories":2336},[189],{"categories":2338},[192],{"categories":2340},[210],{"categories":2342},[189],{"categories":2344},[231],{"categories":2346},[189],{"categories":2348},[189],{"categories":2350},[504],{"categories":2352},[195],{"categories":2354},[192],{"categories":2356},[189],{"categories":2358},[210],{"categories":2360},[192],{"categories":2362},[247],{"categories":2364},[189],{"categories":2366},[],{"categories":2368},[189],{"categories":2370},[],{"categories":2372},[],{"categories":2374},[],{"categories":2376},[186],{"categories":2378},[189],{"categories":2380},[192],{"categories":2382},[210],{"categories":2384},[210],{"categories":2386},[210],{"categories":2388},[210],{"categories":2390},[],{"categories":2392},[183],{"categories":2394},[192],{"categories":2396},[210],{"categories":2398},[183],{"categories":2400},[192],{"categories":2402},[189],{"categories":2404},[189,192],{"categories":2406},[192],{"categories":2408},[504],{"categories":2410},[210],{"categories":2412},[210],{"categories":2414},[192],{"categories":2416},[189],{"categories":2418},[],{"categories":2420},[210],{"categories":2422},[247],{"categories":2424},[183],{"categories":2426},[189],{"categories":2428},[189],{"categories":2430},[],{"categories":2432},[240],{"categories":2434},[],{"categories":2436},[183],{"categories":2438},[192],{"categories":2440},[210],{"categories":2442},[189],{"categories":2444},[210],{"categories":2446},[183],{"categories":2448},[210],{"categories":2450},[210],{"categories":2452},[],{"categories":2454},[186],{"categories":2456},[192],{"categories":2458},[210],{"categories":2460},[210],{"categories":2462},[210],{"categories":2464},[210],{"categories":2466},[210],{"categories":2468},[210],{"categories":2470},[210],{"categories":2472},[210],{"categories":2474},[210],{"categories":2476},[210],{"categories":2478},[160],{"categories":2480},[183],{"categories":2482},[189],{"categories":2484},[189],{"categories":2486},[],{"categories":2488},[189,183],{"categories":2490},[],{"categories":2492},[192],{"categories":2494},[210],{"categories":2496},[192],{"categories":2498},[189],{"categories":2500},[189],{"categories":2502},[189],{"categories":2504},[189],{"categories":2506},[189],{"categories":2508},[192],{"categories":2510},[186],{"categories":2512},[231],{"categories":2514},[210],{"categories":2516},[189],{"categories":2518},[],{"categories":2520},[],{"categories":2522},[192],{"categories":2524},[231],{"categories":2526},[189],{"categories":2528},[],{"categories":2530},[],{"categories":2532},[247],{"categories":2534},[189],{"categories":2536},[],{"categories":2538},[],{"categories":2540},[183],{"categories":2542},[186],{"categories":2544},[189],{"categories":2546},[186],{"categories":2548},[231],{"categories":2550},[],{"categories":2552},[210],{"categories":2554},[],{"categories":2556},[231],{"categories":2558},[189],{"categories":2560},[247],{"categories":2562},[],{"categories":2564},[247],{"categories":2566},[],{"categories":2568},[],{"categories":2570},[192],{"categories":2572},[],{"categories":2574},[186],{"categories":2576},[183],{"categories":2578},[231],{"categories":2580},[240],{"categories":2582},[],{"categories":2584},[],{"categories":2586},[189],{"categories":2588},[183],{"categories":2590},[247],{"categories":2592},[],{"categories":2594},[192],{"categories":2596},[192],{"categories":2598},[210],{"categories":2600},[189],{"categories":2602},[192],{"categories":2604},[189],{"categories":2606},[192],{"categories":2608},[189],{"categories":2610},[195],{"categories":2612},[210],{"categories":2614},[],{"categories":2616},[247],{"categories":2618},[240],{"categories":2620},[192],{"categories":2622},[],{"categories":2624},[189],{"categories":2626},[192],{"categories":2628},[186],{"categories":2630},[183],{"categories":2632},[189],{"categories":2634},[231],{"categories":2636},[240],{"categories":2638},[240],{"categories":2640},[189],{"categories":2642},[160],{"categories":2644},[189],{"categories":2646},[192],{"categories":2648},[186],{"categories":2650},[192],{"categories":2652},[189],{"categories":2654},[189],{"categories":2656},[192],{"categories":2658},[210],{"categories":2660},[],{"categories":2662},[183],{"categories":2664},[189],{"categories":2666},[192],{"categories":2668},[189],{"categories":2670},[189],{"categories":2672},[],{"categories":2674},[231],{"categories":2676},[186],{"categories":2678},[210],{"categories":2680},[189],{"categories":2682},[189],{"categories":2684},[231],{"categories":2686},[247],{"categories":2688},[160],{"categories":2690},[189],{"categories":2692},[210],{"categories":2694},[189],{"categories":2696},[192],{"categories":2698},[504],{"categories":2700},[189],{"categories":2702},[192],{"categories":2704},[160],{"categories":2706},[],{"categories":2708},[192],{"categories":2710},[240],{"categories":2712},[231],{"categories":2714},[189],{"categories":2716},[183],{"categories":2718},[186],{"categories":2720},[240],{"categories":2722},[],{"categories":2724},[192],{"categories":2726},[189],{"categories":2728},[],{"categories":2730},[210],{"categories":2732},[],{"categories":2734},[210],{"categories":2736},[189],{"categories":2738},[192],{"categories":2740},[192],{"categories":2742},[192],{"categories":2744},[],{"categories":2746},[],{"categories":2748},[189],{"categories":2750},[189],{"categories":2752},[],{"categories":2754},[231],{"categories":2756},[192],{"categories":2758},[247],{"categories":2760},[183],{"categories":2762},[],{"categories":2764},[],{"categories":2766},[210],{"categories":2768},[240],{"categories":2770},[189],{"categories":2772},[189],{"categories":2774},[189],{"categories":2776},[240],{"categories":2778},[210],{"categories":2780},[231],{"categories":2782},[189],{"categories":2784},[189],{"categories":2786},[189],{"categories":2788},[210],{"categories":2790},[189],{"categories":2792},[210],{"categories":2794},[192],{"categories":2796},[192],{"categories":2798},[240],{"categories":2800},[192],{"categories":2802},[189],{"categories":2804},[240],{"categories":2806},[231],{"categories":2808},[],{"categories":2810},[192],{"categories":2812},[],{"categories":2814},[],{"categories":2816},[],{"categories":2818},[186],{"categories":2820},[189],{"categories":2822},[192],{"categories":2824},[183],{"categories":2826},[192],{"categories":2828},[247],{"categories":2830},[],{"categories":2832},[192],{"categories":2834},[],{"categories":2836},[183],{"categories":2838},[192],{"categories":2840},[],{"categories":2842},[192],{"categories":2844},[189],{"categories":2846},[210],{"categories":2848},[189],{"categories":2850},[192],{"categories":2852},[210],{"categories":2854},[192],{"categories":2856},[240],{"categories":2858},[231],{"categories":2860},[183],{"categories":2862},[],{"categories":2864},[192],{"categories":2866},[231],{"categories":2868},[504],{"categories":2870},[210],{"categories":2872},[189],{"categories":2874},[231],{"categories":2876},[183],{"categories":2878},[],{"categories":2880},[192],{"categories":2882},[192],{"categories":2884},[189],{"categories":2886},[],{"categories":2888},[192],{"categories":2890},[195],{"categories":2892},[210],{"categories":2894},[192],{"categories":2896},[186],{"categories":2898},[],{"categories":2900},[189],{"categories":2902},[195],{"categories":2904},[189],{"categories":2906},[192],{"categories":2908},[210],{"categories":2910},[183],{"categories":2912},[504],{"categories":2914},[189],{"categories":2916},[189],{"categories":2918},[189],{"categories":2920},[210],{"categories":2922},[186],{"categories":2924},[189],{"categories":2926},[231],{"categories":2928},[210],{"categories":2930},[504],{"categories":2932},[189],{"categories":2934},[],{"categories":2936},[],{"categories":2938},[504],{"categories":2940},[160],{"categories":2942},[192],{"categories":2944},[192],{"categories":2946},[210],{"categories":2948},[189],{"categories":2950},[183],{"categories":2952},[231],{"categories":2954},[192],{"categories":2956},[189],{"categories":2958},[247],{"categories":2960},[189],{"categories":2962},[192],{"categories":2964},[],{"categories":2966},[189],{"categories":2968},[189],{"categories":2970},[210],{"categories":2972},[183],{"categories":2974},[],{"categories":2976},[189],{"categories":2978},[189],{"categories":2980},[240],{"categories":2982},[231],{"categories":2984},[189,192],{"categories":2986},[247,186],{"categories":2988},[189],{"categories":2990},[],{"categories":2992},[192],{"categories":2994},[],{"categories":2996},[240],{"categories":2998},[189],{"categories":3000},[210],{"categories":3002},[],{"categories":3004},[192],{"categories":3006},[],{"categories":3008},[231],{"categories":3010},[192],{"categories":3012},[183],{"categories":3014},[192],{"categories":3016},[189],{"categories":3018},[504],{"categories":3020},[247],{"categories":3022},[186],{"categories":3024},[186],{"categories":3026},[183],{"categories":3028},[183],{"categories":3030},[189],{"categories":3032},[192],{"categories":3034},[189],{"categories":3036},[189],{"categories":3038},[183],{"categories":3040},[189],{"categories":3042},[247],{"categories":3044},[210],{"categories":3046},[189],{"categories":3048},[192],{"categories":3050},[189],{"categories":3052},[],{"categories":3054},[240],{"categories":3056},[],{"categories":3058},[192],{"categories":3060},[183],{"categories":3062},[],{"categories":3064},[504],{"categories":3066},[189],{"categories":3068},[],{"categories":3070},[210],{"categories":3072},[192],{"categories":3074},[240],{"categories":3076},[189],{"categories":3078},[192],{"categories":3080},[240],{"categories":3082},[192],{"categories":3084},[210],{"categories":3086},[183],{"categories":3088},[210],{"categories":3090},[240],{"categories":3092},[189],{"categories":3094},[231],{"categories":3096},[189],{"categories":3098},[189],{"categories":3100},[189],{"categories":3102},[189],{"categories":3104},[192],{"categories":3106},[189],{"categories":3108},[192],{"categories":3110},[189],{"categories":3112},[183],{"categories":3114},[189],{"categories":3116},[192],{"categories":3118},[231],{"categories":3120},[183],{"categories":3122},[192],{"categories":3124},[231],{"categories":3126},[],{"categories":3128},[189],{"categories":3130},[189],{"categories":3132},[240],{"categories":3134},[],{"categories":3136},[192],{"categories":3138},[247],{"categories":3140},[189],{"categories":3142},[210],{"categories":3144},[247],{"categories":3146},[192],{"categories":3148},[186],{"categories":3150},[186],{"categories":3152},[189],{"categories":3154},[183],{"categories":3156},[],{"categories":3158},[189],{"categories":3160},[],{"categories":3162},[183],{"categories":3164},[189],{"categories":3166},[192],{"categories":3168},[192],{"categories":3170},[],{"categories":3172},[240],{"categories":3174},[240],{"categories":3176},[247],{"categories":3178},[231],{"categories":3180},[],{"categories":3182},[189],{"categories":3184},[183],{"categories":3186},[189],{"categories":3188},[240],{"categories":3190},[183],{"categories":3192},[210],{"categories":3194},[210],{"categories":3196},[],{"categories":3198},[210],{"categories":3200},[192],{"categories":3202},[231],{"categories":3204},[160],{"categories":3206},[189],{"categories":3208},[],{"categories":3210},[210],{"categories":3212},[240],{"categories":3214},[186],{"categories":3216},[189],{"categories":3218},[183],{"categories":3220},[504],{"categories":3222},[183],{"categories":3224},[],{"categories":3226},[],{"categories":3228},[210],{"categories":3230},[],{"categories":3232},[192],{"categories":3234},[192],{"categories":3236},[192],{"categories":3238},[],{"categories":3240},[189],{"categories":3242},[],{"categories":3244},[210],{"categories":3246},[183],{"categories":3248},[231],{"categories":3250},[189],{"categories":3252},[210],{"categories":3254},[210],{"categories":3256},[],{"categories":3258},[210],{"categories":3260},[183],{"categories":3262},[189],{"categories":3264},[],{"categories":3266},[192],{"categories":3268},[192],{"categories":3270},[183],{"categories":3272},[],{"categories":3274},[],{"categories":3276},[],{"categories":3278},[231],{"categories":3280},[192],{"categories":3282},[189],{"categories":3284},[],{"categories":3286},[],{"categories":3288},[],{"categories":3290},[231],{"categories":3292},[],{"categories":3294},[183],{"categories":3296},[],{"categories":3298},[],{"categories":3300},[231],{"categories":3302},[189],{"categories":3304},[210],{"categories":3306},[],{"categories":3308},[247],{"categories":3310},[210],{"categories":3312},[247],{"categories":3314},[189],{"categories":3316},[],{"categories":3318},[],{"categories":3320},[192],{"categories":3322},[],{"categories":3324},[],{"categories":3326},[192],{"categories":3328},[189],{"categories":3330},[],{"categories":3332},[192],{"categories":3334},[210],{"categories":3336},[247],{"categories":3338},[160],{"categories":3340},[192],{"categories":3342},[192],{"categories":3344},[],{"categories":3346},[],{"categories":3348},[],{"categories":3350},[210],{"categories":3352},[],{"categories":3354},[],{"categories":3356},[231],{"categories":3358},[183],{"categories":3360},[],{"categories":3362},[186],{"categories":3364},[247],{"categories":3366},[189],{"categories":3368},[240],{"categories":3370},[183],{"categories":3372},[160],{"categories":3374},[186],{"categories":3376},[240],{"categories":3378},[],{"categories":3380},[],{"categories":3382},[192],{"categories":3384},[183],{"categories":3386},[231],{"categories":3388},[183],{"categories":3390},[192],{"categories":3392},[504],{"categories":3394},[192],{"categories":3396},[],{"categories":3398},[189],{"categories":3400},[210],{"categories":3402},[240],{"categories":3404},[],{"categories":3406},[231],{"categories":3408},[210],{"categories":3410},[183],{"categories":3412},[192],{"categories":3414},[189],{"categories":3416},[186],{"categories":3418},[192,504],{"categories":3420},[192],{"categories":3422},[240],{"categories":3424},[189],{"categories":3426},[160],{"categories":3428},[247],{"categories":3430},[192],{"categories":3432},[],{"categories":3434},[192],{"categories":3436},[189],{"categories":3438},[186],{"categories":3440},[],{"categories":3442},[],{"categories":3444},[189],{"categories":3446},[160],{"categories":3448},[189],{"categories":3450},[],{"categories":3452},[210],{"categories":3454},[],{"categories":3456},[210],{"categories":3458},[240],{"categories":3460},[192],{"categories":3462},[189],{"categories":3464},[247],{"categories":3466},[240],{"categories":3468},[],{"categories":3470},[210],{"categories":3472},[189],{"categories":3474},[],{"categories":3476},[189],{"categories":3478},[192],{"categories":3480},[189],{"categories":3482},[192],{"categories":3484},[189],{"categories":3486},[189],{"categories":3488},[189],{"categories":3490},[189],{"categories":3492},[186],{"categories":3494},[],{"categories":3496},[195],{"categories":3498},[210],{"categories":3500},[189],{"categories":3502},[],{"categories":3504},[240],{"categories":3506},[189],{"categories":3508},[189],{"categories":3510},[192],{"categories":3512},[210],{"categories":3514},[189],{"categories":3516},[189],{"categories":3518},[186],{"categories":3520},[192],{"categories":3522},[231],{"categories":3524},[],{"categories":3526},[160],{"categories":3528},[189],{"categories":3530},[],{"categories":3532},[210],{"categories":3534},[247],{"categories":3536},[],{"categories":3538},[],{"categories":3540},[210],{"categories":3542},[210],{"categories":3544},[247],{"categories":3546},[183],{"categories":3548},[192],{"categories":3550},[192],{"categories":3552},[189],{"categories":3554},[186],{"categories":3556},[],{"categories":3558},[],{"categories":3560},[210],{"categories":3562},[160],{"categories":3564},[240],{"categories":3566},[192],{"categories":3568},[231],{"categories":3570},[160],{"categories":3572},[160],{"categories":3574},[],{"categories":3576},[210],{"categories":3578},[189],{"categories":3580},[189],{"categories":3582},[240],{"categories":3584},[],{"categories":3586},[210],{"categories":3588},[210],{"categories":3590},[210],{"categories":3592},[],{"categories":3594},[192],{"categories":3596},[189],{"categories":3598},[],{"categories":3600},[183],{"categories":3602},[186],{"categories":3604},[],{"categories":3606},[189],{"categories":3608},[189],{"categories":3610},[],{"categories":3612},[240],{"categories":3614},[],{"categories":3616},[],{"categories":3618},[],{"categories":3620},[],{"categories":3622},[189],{"categories":3624},[210],{"categories":3626},[],{"categories":3628},[],{"categories":3630},[189],{"categories":3632},[189],{"categories":3634},[189],{"categories":3636},[160],{"categories":3638},[189],{"categories":3640},[160],{"categories":3642},[],{"categories":3644},[160],{"categories":3646},[160],{"categories":3648},[504],{"categories":3650},[192],{"categories":3652},[240],{"categories":3654},[],{"categories":3656},[],{"categories":3658},[160],{"categories":3660},[240],{"categories":3662},[240],{"categories":3664},[240],{"categories":3666},[],{"categories":3668},[183],{"categories":3670},[240],{"categories":3672},[240],{"categories":3674},[183],{"categories":3676},[240],{"categories":3678},[186],{"categories":3680},[240],{"categories":3682},[240],{"categories":3684},[240],{"categories":3686},[160],{"categories":3688},[210],{"categories":3690},[210],{"categories":3692},[189],{"categories":3694},[240],{"categories":3696},[160],{"categories":3698},[504],{"categories":3700},[160],{"categories":3702},[160],{"categories":3704},[160],{"categories":3706},[],{"categories":3708},[186],{"categories":3710},[],{"categories":3712},[504],{"categories":3714},[240],{"categories":3716},[240],{"categories":3718},[240],{"categories":3720},[192],{"categories":3722},[210,186],{"categories":3724},[160],{"categories":3726},[],{"categories":3728},[],{"categories":3730},[160],{"categories":3732},[],{"categories":3734},[160],{"categories":3736},[210],{"categories":3738},[192],{"categories":3740},[],{"categories":3742},[240],{"categories":3744},[189],{"categories":3746},[231],{"categories":3748},[],{"categories":3750},[189],{"categories":3752},[],{"categories":3754},[210],{"categories":3756},[183],{"categories":3758},[160],{"categories":3760},[],{"categories":3762},[240],{"categories":3764},[210],[3766,3832,3954,4049],{"id":3767,"title":3768,"ai":3769,"body":3774,"categories":3802,"created_at":161,"date_modified":161,"description":80,"extension":162,"faq":161,"featured":163,"kicker_label":161,"meta":3803,"navigation":165,"path":3819,"published_at":3820,"question":161,"scraped_at":3821,"seo":3822,"sitemap":3823,"source_id":3824,"source_name":3825,"source_type":172,"source_url":3826,"stem":3827,"tags":3828,"thumbnail_url":161,"tldr":3829,"tweet":161,"unknown_tags":3830,"__hash__":3831},"summaries\u002Fsummaries\u002F092f953f13e749e1-reproduce-2011-sentiment-word-vectors-in-python-summary.md","Reproduce 2011 Sentiment Word Vectors in Python",{"provider":7,"model":8,"input_tokens":3770,"output_tokens":3771,"processing_time_ms":3772,"cost_usd":3773},3933,1516,16200,0.00152195,{"type":14,"value":3775,"toc":3797},[3776,3780,3783,3787,3790,3794],[17,3777,3779],{"id":3778},"elegant-core-technique-semantic-learning-from-ratings","Elegant Core Technique: Semantic Learning from Ratings",[22,3781,3782],{},"Maas et al. (2011) train sentiment-specific word vectors directly from unlabeled IMDb movie reviews paired with star ratings (1-10 scale). Words co-occurring in high-rated reviews pull closer in vector space; low-rated push apart. This creates representations capturing sentiment polarity without explicit labels. Final classification uses linear SVM on averaged review vectors, achieving strong accuracy through interpretable, low-dimensional embeddings. Author notes its logistic regression-like simplicity: powerful when data aligns with task, avoiding black-box complexity.",[17,3784,3786],{"id":3785},"reproduction-insights-and-modern-relevance","Reproduction Insights and Modern Relevance",[22,3788,3789],{},"Reproducing the paper in Python reveals its enduring strength – elegant semantic learning outperforms hype-driven alternatives in targeted tasks like sentiment. Author challenges original methods, tests against other representations (including LLMs), and automates full pipeline. Trade-off: excels on review-style text but needs domain data; not general-purpose like transformers. GitHub repo provides end-to-end code for immediate use or extension.",[17,3791,3793],{"id":3792},"practical-takeaways-for-builders","Practical Takeaways for Builders",[22,3795,3796],{},"Start with this for sentiment features in products: download IMDb data, train vectors via contrastive objective on ratings, classify with SVM. Scales to custom corpora (e.g., product feedback). Compares favorably to LLMs on cost\u002Finterpretability; use as baseline before deploying APIs. Avoids overfitting by leveraging vast unlabeled text – key for production ML pipelines.",{"title":80,"searchDepth":154,"depth":154,"links":3798},[3799,3800,3801],{"id":3778,"depth":154,"text":3779},{"id":3785,"depth":154,"text":3786},{"id":3792,"depth":154,"text":3793},[160],{"content_references":3804,"triage":3814},[3805,3810],{"type":3806,"title":3807,"author":3808,"context":3809},"paper","Learning Word Vectors for Sentiment Analysis","Maas et al.","mentioned",{"type":3811,"title":3812,"url":3813,"context":3809},"other","Sentiment_analysis","https:\u002F\u002Fgithub.com\u002FJumbong\u002FSentiment_analysis",{"relevance":3815,"novelty":3816,"quality":3816,"actionability":3815,"composite":3817,"reasoning":3818},5,4,4.55,"Category: AI & LLMs. The article provides a practical method for building sentiment-aware word embeddings, which is directly applicable for product builders looking to integrate sentiment analysis into their AI-powered products. It includes actionable steps and a GitHub repository for implementation, making it highly relevant and actionable.","\u002Fsummaries\u002F092f953f13e749e1-reproduce-2011-sentiment-word-vectors-in-python-summary","2026-05-10 00:01:00","2026-05-10 15:26:28",{"title":3768,"description":80},{"loc":3819},"092f953f13e749e1","Towards AI","https:\u002F\u002Fpub.towardsai.net\u002Flearning-word-vectors-for-sentiment-analysis-a-python-reproduction-f8c8c77df38f?source=rss----98111c9905da---4","summaries\u002F092f953f13e749e1-reproduce-2011-sentiment-word-vectors-in-python-summary",[79,176],"Build sentiment-aware word embeddings from IMDb reviews via semantic learning with star ratings and linear SVM classification, reproducing Maas et al. (2011) – simple method rivals modern LLMs.",[],"v2XTBE5rFNMZcIts4tjxKmc0d5a3j51Waw-d4ggTQcI",{"id":3833,"title":3834,"ai":3835,"body":3840,"categories":3941,"created_at":161,"date_modified":161,"description":80,"extension":162,"faq":161,"featured":163,"kicker_label":161,"meta":3942,"navigation":165,"path":3943,"published_at":3944,"question":161,"scraped_at":161,"seo":3945,"sitemap":3946,"source_id":3947,"source_name":3948,"source_type":172,"source_url":173,"stem":3949,"tags":3950,"thumbnail_url":161,"tldr":3951,"tweet":161,"unknown_tags":3952,"__hash__":3953},"summaries\u002Fsummaries\u002Ffix-randomness-first-for-stable-ml-pipelines-summary.md","Fix Randomness First for Stable ML Pipelines",{"provider":7,"model":8,"input_tokens":3836,"output_tokens":3837,"processing_time_ms":3838,"cost_usd":3839},3629,1311,12564,0.0013588,{"type":14,"value":3841,"toc":3937},[3842,3846,3849,3853,3856,3922,3929,3935],[17,3843,3845],{"id":3844},"pipelines-not-models-break-ml-systems","Pipelines, Not Models, Break ML Systems",[22,3847,3848],{},"After 4+ years building ML systems, the core failure mode isn't weak models but unstable pipelines that produce inconsistent results. A one-time success turns into quiet failures without disciplined stability practices. Treat stability as a non-negotiable discipline, not an afterthought.",[17,3850,3852],{"id":3851},"enforce-reproducibility-by-seeding-everything","Enforce Reproducibility by Seeding Everything",[22,3854,3855],{},"Randomness turns models into unreliable slot machines—results vary per run, undermining debugging and deployment. Fix it with a global seed function covering all sources:",[75,3857,3859],{"className":77,"code":3858,"language":79,"meta":80,"style":80},"import random\nimport numpy as np\nimport torch\n\ndef set_seed(seed=42):\n    random.seed(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed_all(seed)\n\nset_seed(42)\n",[82,3860,3861,3866,3871,3877,3882,3887,3893,3899,3905,3911,3916],{"__ignoreMap":80},[36,3862,3863],{"class":86,"line":87},[36,3864,3865],{},"import random\n",[36,3867,3868],{"class":86,"line":154},[36,3869,3870],{},"import numpy as np\n",[36,3872,3874],{"class":86,"line":3873},3,[36,3875,3876],{},"import torch\n",[36,3878,3879],{"class":86,"line":3816},[36,3880,3881],{"emptyLinePlaceholder":165},"\n",[36,3883,3884],{"class":86,"line":3815},[36,3885,3886],{},"def set_seed(seed=42):\n",[36,3888,3890],{"class":86,"line":3889},6,[36,3891,3892],{},"    random.seed(seed)\n",[36,3894,3896],{"class":86,"line":3895},7,[36,3897,3898],{},"    np.random.seed(seed)\n",[36,3900,3902],{"class":86,"line":3901},8,[36,3903,3904],{},"    torch.manual_seed(seed)\n",[36,3906,3908],{"class":86,"line":3907},9,[36,3909,3910],{},"    torch.cuda.manual_seed_all(seed)\n",[36,3912,3914],{"class":86,"line":3913},10,[36,3915,3881],{"emptyLinePlaceholder":165},[36,3917,3919],{"class":86,"line":3918},11,[36,3920,3921],{},"set_seed(42)\n",[22,3923,3924,3925,3928],{},"Call this early. ",[127,3926,3927],{},"Key caveat:"," Seeds don't fully eliminate non-determinism in some GPU operations—explicitly configure those for true reproducibility.",[22,3930,3931],{},[3932,3933,3934],"em",{},"Note: Article outlines 9 rules total but details only the first here.",[150,3936,152],{},{"title":80,"searchDepth":154,"depth":154,"links":3938},[3939,3940],{"id":3844,"depth":154,"text":3845},{"id":3851,"depth":154,"text":3852},[160],{},"\u002Fsummaries\u002Ffix-randomness-first-for-stable-ml-pipelines-summary","2026-04-08 21:21:17",{"title":3834,"description":80},{"loc":3943},"ed293f2ee2f46e73","Python in Plain English","summaries\u002Ffix-randomness-first-for-stable-ml-pipelines-summary",[79,176],"ML systems fail from unstable pipelines, not bad models—control randomness by setting seeds across random, NumPy, and PyTorch to ensure reproducible results.",[],"w_GpfcH_eP9a4oHynSujBQl1BptGg4S_T_nFYUIStoo",{"id":3955,"title":3956,"ai":3957,"body":3962,"categories":4038,"created_at":161,"date_modified":161,"description":80,"extension":162,"faq":161,"featured":163,"kicker_label":161,"meta":4039,"navigation":165,"path":4040,"published_at":167,"question":161,"scraped_at":161,"seo":4041,"sitemap":4042,"source_id":4043,"source_name":171,"source_type":172,"source_url":173,"stem":4044,"tags":4045,"thumbnail_url":161,"tldr":4046,"tweet":161,"unknown_tags":4047,"__hash__":4048},"summaries\u002Fsummaries\u002Fpytorch-nn-linear-mismatches-raw-matmul-by-1e-4-summary.md","PyTorch nn.Linear Mismatches Raw Matmul by 1e-4",{"provider":7,"model":8,"input_tokens":3958,"output_tokens":3959,"processing_time_ms":3960,"cost_usd":3961},3920,1128,10617,0.00088105,{"type":14,"value":3963,"toc":4033},[3964,3968,3991,3995,4014,4018],[17,3965,3967],{"id":3966},"raw-matmul-preserves-precision-across-batch-sizes","Raw Matmul Preserves Precision Across Batch Sizes",[22,3969,3970,3971,3974,3975,3978,3979,3982,3983,3986,3987,3990],{},"Use ",[82,3972,3973],{},"torch.matmul"," for exact equivalence: with seed 42, ",[82,3976,3977],{},"x = torch.randn(2, 768)"," and ",[82,3980,3981],{},"w = torch.randn(768, 768)",", computing ",[82,3984,3985],{},"z1 = x[0] @ w"," matches ",[82,3988,3989],{},"(x @ w)[0]"," exactly—max absolute difference is 0. This holds because PyTorch's matrix multiply ignores batch dimensions consistently without introducing fusion artifacts.",[17,3992,3994],{"id":3993},"nnlinear-introduces-numerical-drift","nn.Linear Introduces Numerical Drift",[22,3996,3997,3998,4001,4002,4005,4006,4009,4010,4013],{},"nn.Linear(768, 768, bias=False) with weight copied from ",[82,3999,4000],{},"w.T"," fails exactness. ",[82,4003,4004],{},"q1 = m(x[0])"," differs from ",[82,4007,4008],{},"q2 = m(x)[0]"," by max ~2e-5, and both deviate from raw ",[82,4011,4012],{},"z1"," by ~9e-5. Avoid assuming single-sample Linear matches batched or raw matmul outputs—use raw ops for precision-critical math.",[17,4015,4017],{"id":4016},"root-cause-fused-operations-in-batched-mode","Root Cause: Fused Operations in Batched Mode",[22,4019,4020,4021,4024,4025,4028,4029,4032],{},"Commenter notes torch source shows fused kernels activate differently for batched (shape ",[36,4022,4023],{},"2,768",") vs single (",[36,4026,4027],{},"768",") inputs, causing drift. Test by disabling autocast or fusions (e.g., ",[82,4030,4031],{},"torch.backends.cudnn.deterministic=True",") to isolate; impacts model debugging where exact reproducibility matters over speed.",{"title":80,"searchDepth":154,"depth":154,"links":4034},[4035,4036,4037],{"id":3966,"depth":154,"text":3967},{"id":3993,"depth":154,"text":3994},{"id":4016,"depth":154,"text":4017},[240],{},"\u002Fsummaries\u002Fpytorch-nn-linear-mismatches-raw-matmul-by-1e-4-summary",{"title":3956,"description":80},{"loc":4040},"c31c04ed51f90c10","summaries\u002Fpytorch-nn-linear-mismatches-raw-matmul-by-1e-4-summary",[79,176],"Raw torch.matmul gives identical results for single vs batched inputs (diff=0), but nn.Linear differs by 2e-5 between single\u002Fbatched and 9e-5 from raw matmul due to fused ops.",[],"N4HIPkktA2CpEJX7Wbl2sDkMuAd2ARWc4-gOQSjiAUA",{"id":4050,"title":4051,"ai":4052,"body":4057,"categories":4250,"created_at":161,"date_modified":161,"description":80,"extension":162,"faq":161,"featured":163,"kicker_label":161,"meta":4251,"navigation":165,"path":4263,"published_at":4264,"question":161,"scraped_at":4265,"seo":4266,"sitemap":4267,"source_id":4268,"source_name":4269,"source_type":172,"source_url":4270,"stem":4271,"tags":4272,"thumbnail_url":161,"tldr":4274,"tweet":161,"unknown_tags":4275,"__hash__":4276},"summaries\u002Fsummaries\u002Fff126f8e0954389e-skfolio-build-tune-portfolio-optimizers-in-python-summary.md","skfolio: Build & Tune Portfolio Optimizers in Python",{"provider":7,"model":8,"input_tokens":4053,"output_tokens":4054,"processing_time_ms":4055,"cost_usd":4056},9292,2519,30098,0.00309525,{"type":14,"value":4058,"toc":4244},[4059,4063,4094,4098,4147,4151,4216,4220],[17,4060,4062],{"id":4061},"data-prep-and-baseline-benchmarks-deliver-quick-wins","Data Prep and Baseline Benchmarks Deliver Quick Wins",[22,4064,4065,4066,4069,4070,4073,4074,4077,4078,4081,4082,4085,4086,4089,4090,4093],{},"Load S&P 500 prices via ",[82,4067,4068],{},"skfolio.datasets.load_sp500_dataset()",", convert to returns with ",[82,4071,4072],{},"prices_to_returns()",", and split chronologically (",[82,4075,4076],{},"train_test_split(shuffle=False, test_size=0.33)",") to prevent look-ahead bias—training spans ~67% historical days, testing the rest. Baselines like ",[82,4079,4080],{},"EqualWeighted()",", ",[82,4083,4084],{},"InverseVolatility()",", and ",[82,4087,4088],{},"Random()"," fit on train, predict on test, yielding metrics like annualized Sharpe (printed via ",[82,4091,4092],{},"ptf.annualized_sharpe_ratio","), mean return, and volatility. These expose naive strategies' flaws: equal-weight ignores volatility, random adds noise—use them to benchmark any optimizer.",[17,4095,4097],{"id":4096},"mean-variance-risk-measures-and-clustering-beat-baselines","Mean-Variance, Risk Measures, and Clustering Beat Baselines",[22,4099,4100,4103,4104,4107,4108,4111,4112,4115,4116,4081,4119,4122,4123,4126,4127,4130,4131,4134,4135,4138,4139,4142,4143,4146],{},[82,4101,4102],{},"MeanRisk(risk_measure=RiskMeasure.VARIANCE)"," minimizes variance or maximizes Sharpe (",[82,4105,4106],{},"ObjectiveFunction.MAXIMIZE_RATIO","), generating efficient frontiers (",[82,4109,4110],{},"efficient_frontier_size=20",") plotted by risk vs. Sharpe. Swap risks to ",[82,4113,4114],{},"CVaR"," (95%), ",[82,4117,4118],{},"SEMI_VARIANCE",[82,4120,4121],{},"CDAR",", or ",[82,4124,4125],{},"MAX_DRAWDOWN"," for tail-focused portfolios that cut CVaR@95% and max drawdown vs. variance. ",[82,4128,4129],{},"RiskBudgeting()"," equalizes contributions (variance or CVaR). Hierarchical methods shine: ",[82,4132,4133],{},"HierarchicalRiskParity()"," clusters assets via dendrograms for stable weights; ",[82,4136,4137],{},"NestedClustersOptimization()"," nests ",[82,4140,4141],{},"MeanRisk(CVAR)"," inside ",[82,4144,4145],{},"RiskBudgeting(VARIANCE)"," with 5-fold CV, capturing correlations without covariance pitfalls.",[17,4148,4150],{"id":4149},"robust-priors-constraints-and-views-stabilize-real-world-use","Robust Priors, Constraints, and Views Stabilize Real-World Use",[22,4152,4153,4154,4157,4158,4161,4162,4081,4165,4081,4168,4122,4171,4174,4175,4178,4179,4081,4182,4081,4185,4081,4188,4191,4192,4195,4196,4199,4200,4203,4204,4207,4208,4211,4212,4215],{},"Replace ",[82,4155,4156],{},"EmpiricalCovariance()","\u002F",[82,4159,4160],{},"EmpiricalMu()"," with ",[82,4163,4164],{},"DenoiseCovariance()",[82,4166,4167],{},"ShrunkMu()",[82,4169,4170],{},"GerberCovariance()",[82,4172,4173],{},"EWMu(alpha=0.1)"," in ",[82,4176,4177],{},"EmpiricalPrior()"," for max-Sharpe portfolios resilient to estimation error. Add realism via ",[82,4180,4181],{},"min_weights=0.0",[82,4183,4184],{},"max_weights=0.20",[82,4186,4187],{},"transaction_costs=0.0005",[82,4189,4190],{},"groups"," (e.g., GroupA \u003C=0.6, GroupB>=0.2), ",[82,4193,4194],{},"l2_coef=0.01",". ",[82,4197,4198],{},"BlackLitterman(views=[\"AAPL == 0.0008\", \"JPM - BAC == 0.0002\"])"," blends market priors with views. ",[82,4201,4202],{},"FactorModel()"," on ",[82,4205,4206],{},"load_factors_dataset()"," explains returns via external factors, boosting Sharpe. Pipelines like ",[82,4209,4210],{},"SelectKExtremes(k=8)"," + ",[82,4213,4214],{},"MeanRisk()"," prune to top performers.",[17,4217,4219],{"id":4218},"walk-forward-cv-and-tuning-ensure-out-of-sample-performance","Walk-Forward CV and Tuning Ensure Out-of-Sample Performance",[22,4221,4222,4161,4225,4228,4229,4232,4233,3978,4236,4239,4240,4243],{},[82,4223,4224],{},"cross_val_predict()",[82,4226,4227],{},"WalkForward(train_size=252*2, test_size=63)"," simulates rolling 2-year trains\u002F3-month tests, computing portfolio Sharpe\u002FCalmar. ",[82,4230,4231],{},"GridSearchCV()"," tunes ",[82,4234,4235],{},"l2_coef=[0.0,0.01,0.1]",[82,4237,4238],{},"mu_estimator__alpha=[0.05,0.1,0.2,0.5]"," on max-Sharpe, selecting best CV Sharpe. Final ",[82,4241,4242],{},"Population()"," of 18 strategies compares annualized mean\u002Fvol\u002FSharpe\u002FSortino\u002FCVaR@95%\u002Fdrawdowns (sorted by test Sharpe), with plots for cumulative returns, weights, risk contributions—revealing hierarchical\u002Frisk-parity often top variance-based in stability.",{"title":80,"searchDepth":154,"depth":154,"links":4245},[4246,4247,4248,4249],{"id":4061,"depth":154,"text":4062},{"id":4096,"depth":154,"text":4097},{"id":4149,"depth":154,"text":4150},{"id":4218,"depth":154,"text":4219},[160],{"content_references":4252,"triage":4260},[4253,4257],{"type":4254,"title":4255,"url":4256,"context":3809},"tool","skfolio","https:\u002F\u002Fgithub.com\u002Fskfolio\u002Fskfolio",{"type":3811,"title":4258,"url":4259,"context":3809},"Full Codes","https:\u002F\u002Fgithub.com\u002FMarktechpost\u002FAI-Agents-Projects-Tutorials\u002Fblob\u002Fmain\u002FData%20Science\u002Fportfolio_optimization_with_skfolio_Marktechpost.ipynb",{"relevance":3873,"novelty":3873,"quality":3816,"actionability":3816,"composite":4261,"reasoning":4262},3.45,"Category: Data Science & Visualization. The article provides a practical guide on using the skfolio library for portfolio optimization, which aligns with the audience's interest in actionable AI and data science tools. It includes specific code examples and methodologies that can be directly applied, making it useful for developers looking to implement AI in financial products.","\u002Fsummaries\u002Fff126f8e0954389e-skfolio-build-tune-portfolio-optimizers-in-python-summary","2026-05-12 07:05:02","2026-05-12 15:01:25",{"title":4051,"description":80},{"loc":4263},"ff126f8e0954389e","MarkTechPost","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F05\u002F12\u002Fa-coding-implementation-to-portfolio-optimization-with-skfolio-for-building-testing-tuning-and-comparing-modern-investment-strategies\u002F","summaries\u002Fff126f8e0954389e-skfolio-build-tune-portfolio-optimizers-in-python-summary",[79,4273,176],"data-science","skfolio's scikit-learn API lets you construct, validate, and compare 18+ portfolio strategies—from baselines to HRP, Black-Litterman, factors, and tuned models—on S&P 500 returns with walk-forward CV and GridSearchCV.",[],"s9QUFNF_HWzNZV61Dh6PEETN3C3-K3FsZalb0rd3HRQ"]