From 6fa80efc1c53905b6328c5b44df3db4e4da34dfe Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 12:59:25 -0500 Subject: results: close Oral-A v3 causal-capture gate --- RESULTS.md | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'RESULTS.md') diff --git a/RESULTS.md b/RESULTS.md index 50377ba..9a6fa81 100644 --- a/RESULTS.md +++ b/RESULTS.md @@ -683,6 +683,30 @@ post-failure oracle diagnostics, not trainable-method results. They rule out a naive basis expansion and point toward both better causal sample efficiency and a more informative hierarchical/high-level feedback context. +V3 tests whether the remaining regression gap comes specifically from +estimating per-example coefficients before fitting A/G. It perturbs random A/G +matrices directly, so each induced hidden intervention already contains the +output-error context and the antithetic scalar estimates the exact matrix +statistic needed by the vectorizer delta rule. Mechanics are strong: at batch +128 the frozen synthetic one-query MSE is `0.03381x` the coefficient estimator, +and exact no-BN/BN JVP errors are below `2e-10`. + +That gain does not transfer to early ResNet credit. All four frozen-forward +records are finite and the selected rate is again `eta_A=0.01`: + +| estimator | early-third alignment | all-layer alignment | +|:--|--:|--:| +| channel-subspace V2 reference | 0.007209 | 0.052740 | +| vectorizer-subspace V3 | 0.007139 | 0.062579 | + +The common all-layer endpoint improves, but the early endpoint is unchanged +and misses three frozen advancement checks. Higher rates are worse. Thus the +coefficient-regression stage was not the dominant early-layer limitation under +the real causal signal. V3-2 is not launched. The result redirects development +toward informative hierarchical/high-level feedback context or a mechanism +that addresses remaining cross-layer/parameter-space noise; it does not +justify another rate or warmup sweep. + ## How to run `experiments/run.py --mode {bp,fa,dfa,sdil} --dataset {mnist,fmnist,cifar10} --depth D --residual {0,1} --act {tanh,gelu,silu,relu}` Batteries: `experiments/run_v2.sh "" "" `. -- cgit v1.2.3