| Age | Commit message (Collapse) | Author |
|---|
|
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>
|
|
BP Gamma: raw~0.99, filtered=1.000 (confirms self-cosine artifact from zero grads)
DFA Gamma (synth): raw~0.01-0.16, filtered~0.01-0.17 (minimal filtering effect)
DFA Gamma (CIFAR): raw=0.107, filtered=0.466 (99.7% samples have near-zero BP grad!)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
|
Formula: ||h_{L//2} - h_L||_2 / ||h_L||_2 (scalar L2 ratio)
A1: 240 rows (3 alpha × 2 depth × 4 methods × 10 seeds)
A2: 40 rows (4 methods including BP × 10 seeds)
All model checkpoints saved in checkpoints_A1/ and checkpoints_A2/
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
|
BP 10-seed results: acc=0.614±0.003, Gamma=1.0, rho=0.998
Appended to A2_cifar_state_vs_credit.csv and A2_naive_state_err.csv
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
|
A1: 240 rows (3 alpha × 2 depth × 4 methods × 10 seeds)
A2: 30 rows (3 methods × 10 seeds)
naive_StateErr = ||h_{L//2} - h_L|| / ||h_L||
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
|
A1: Synthetic nonlinearity ladder (240 rows: 3 alpha × 2 depth × 4 methods × 10 seeds)
A2: CIFAR state-vs-credit counterexample (30 rows: 3 methods × 10 seeds)
A3: Frozen vs online dissociation (60 rows: 2 regimes × 3 methods × 10 seeds)
A4: Protocol dependence panel (82 rows: assembled from existing results)
All experiments ran on GPU 3. Total runtime: ~20 hours.
CSVs in results/confirmatory/.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
