faeval.git/experiments/bp_support_sparsity.py, branch master Unnamed repository; edit this file 'description' to name the repository. Add BP support sparsity analysis: threshold sweep + gradient histograms 2026-04-01T14:54:31+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-01T14:54:31+00:00 a0ec1a6c17b72a3ab769fb8c12f5ef381f38beed A1 Synthetic: all methods have >93% support at τ=1e-6 (gradients rarely zero) A2 CIFAR: massive gap — BP 98.4% vs DFA 0.4% vs SB 21% vs CB 3% DFA-trained CIFAR networks have near-zero BP gradients for 99.6% of samples This explains why Gamma is unreliable for CIFAR non-BP methods Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> 
A1 Synthetic: all methods have >93% support at τ=1e-6 (gradients rarely zero)
A2 CIFAR: massive gap — BP 98.4% vs DFA 0.4% vs SB 21% vs CB 3%
  DFA-trained CIFAR networks have near-zero BP gradients for 99.6% of samples
  This explains why Gamma is unreliable for CIFAR non-BP methods

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