diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-01 09:59:39 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-01 09:59:39 -0500 |
| commit | 6315e18de1b8640ddf4a818c767f3fc14cc5001e (patch) | |
| tree | 847375d7f08fca727fbc915cf605e702a9019473 /results/confirmatory/clean_sparsity/synth_dfa_s1024_a0.0_L4.json | |
| parent | a0ec1a6c17b72a3ab769fb8c12f5ef381f38beed (diff) | |
Add extended sparsity analysis: A4 per-layer, B1 snapshots, B2 active subset, C1/C2
A4: Per-layer support — DFA/SB/CB layers 1-3 have 0% support at τ=1e-6
Only BP has ~95% support; only SB layer 0 has 53%
B1: Snapshot evolution — old snapshot checkpoints have near-zero grads (data issue)
B2: Active subset — with τ=1e-6, no active samples for non-BP methods
C1: Active vs inactive cosine — only inactive subset exists for non-BP
C2: Energy concentration — near-zero for non-BP methods
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'results/confirmatory/clean_sparsity/synth_dfa_s1024_a0.0_L4.json')
0 files changed, 0 insertions, 0 deletions