From 5789cf1358542a3216761e578d5d87e021dec35c Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 03:18:54 -0500 Subject: results: mark useful-depth BP screen passed --- RESULTS.md | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'RESULTS.md') diff --git a/RESULTS.md b/RESULTS.md index 14c9f2b..d98e89d 100644 --- a/RESULTS.md +++ b/RESULTS.md @@ -276,6 +276,28 @@ DFA's teaching signal to early/deep layers collapses toward random (~0.05–0.19 SDIL stays ~0.85 and is depth-invariant. This is the "does credit reach early layers" metric that DFA fails and SDIL passes — the core advantage. +## C2 BP useful-depth screen (validation only) + +The frozen candidate uses a two-level Telgarsky tent-map task, width-8 ReLU residual networks, +and three independently generated task/data seeds. Student initialization is fixed at seed 0 for +this shape screen. All 15 runs came from clean revision `76688af`, used stratified validation +subsets drawn only from generated training data, and never evaluated the independent test sets. + +| depth | validation acc (%) | task-seed endpoints (%) | final-third lesion drops (points) | +|------:|-------------------:|:------------------------|:---------------------------------| +| 1 | 63.933 ± 10.272 | 75.25, 55.20, 61.35 | — | +| 2 | 60.883 ± 7.243 | 57.85, 69.15, 55.65 | +14.25, +24.75, +15.10 | +| 3 | 97.250 ± 1.097 | 96.30, 97.00, 98.45 | +58.80, +58.75, +60.15 | +| 4 | 96.883 ± 1.457 | 97.35, 98.05, 95.25 | +40.85, +35.05, +34.85 | +| 6 | 90.733 ± 7.743 | 96.35, 93.95, 81.90 | +40.05, +40.35, -2.10 | + +For the preselected d1-to-d4 comparison, paired BP gains are `+22.10`, `+42.85`, and `+33.90` +points (mean `+32.95`). The corresponding final-third lesion drops average `36.92` points and are +positive for every task seed. **The BP useful-depth sub-gate passes.** The nonmonotonic curve is +also informative: d2 can optimize worse than d1, and d6 is less stable than d3/d4. The claim is +therefore about a verified useful-depth pair, not monotonic improvement from adding arbitrary +blocks. + ## Paper-faithful non-backprop baselines `PETITE` in the initial request is treated as **PEPITA**. Implementations and hyperparameters were -- cgit v1.2.3