diff options
Diffstat (limited to 'RESULTS.md')
| -rw-r--r-- | RESULTS.md | 4 |
1 files changed, 3 insertions, 1 deletions
@@ -170,7 +170,9 @@ within noise (97.13% vs 97.04% last-epoch mean), again with a ~26x wall-time adv `experiments/run.py --mode {bp,dfa,sdil} --dataset {mnist,fmnist,cifar10} --depth D --residual {0,1} --act {tanh,gelu,silu,relu}` Batteries: `experiments/run_v2.sh <ds> "<depths>" <res> <act> "<seeds>" <ep> <pfx>`. Canonical local baselines: `experiments/baseline_sweep.sh`; original d1 EP: -`experiments/ep_original_sweep.sh`; EP comparison: `experiments/ep_matched_sweep.sh`. +`experiments/ep_original_sweep.sh`; exact d1 comparison: `experiments/ep_archmatch_sweep.sh`; +canonical d2 comparison: `experiments/ep_depth2_sweep.sh`; near-parameter comparison: +`experiments/ep_matched_sweep.sh`. Audited aggregate tables: `experiments/analyze_verified.py`. Smoke/mechanism checks: `experiments/smoke.py` and `experiments/baseline_smoke.py`. |