faeval.git/results/confirmatory/clean_sparsity/cifar_ep_s123.json, branch master Unnamed repository; edit this file 'description' to name the repository. Add EP to BP gradient sparsity analysis 2026-04-03T15:37:49+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-03T15:37:49+00:00 593628cec3cd75eee1033e7a8d6bc4572de5a543 EP CIFAR d=256: s(1e-6)=100%, mean_norm=1.41e-04 EP produces networks where ALL samples have non-zero BP gradients, unlike DFA (0.4%), SB (21%), CB (3%). EP is closer to BP (98.7%). Updated clean_sparsity_summary.csv (980 rows, now includes EP). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
EP CIFAR d=256: s(1e-6)=100%, mean_norm=1.41e-04
EP produces networks where ALL samples have non-zero BP gradients,
unlike DFA (0.4%), SB (21%), CB (3%). EP is closer to BP (98.7%).

Updated clean_sparsity_summary.csv (980 rows, now includes EP).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>