From d841aa67aea64ef735c29e063829f36dc3c5d7de Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 12:52:05 -0500 Subject: algorithm: estimate causal credit in vectorizer space --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'README.md') diff --git a/README.md b/README.md index 4d4d3df..61f42de 100644 --- a/README.md +++ b/README.md @@ -110,6 +110,13 @@ path: it perturbs the channel-gated basis directly and reproduces the expected full-field delta rule with far less irrelevant spatial variance. It does not retroactively reopen or relabel the failed frozen Oral-A protocol. +The subsequent V3 mechanism estimates the required A/G matrix statistics +directly by perturbing the vectorizer parameter subspace. It remains +forward-only and uses two causal loss queries per direction. Its exact and +BatchNorm JVP identities, delta rule, and matched synthetic variance comparison +are covered by `experiments/conv_local_smoke.py`; no task-level claim is made +until a new frozen gate is completed. + `experiments/finalize_accept.sh` additionally requires strict imports of the frozen BurstCCN and Dual Propagation author-code runs. Both records now pass; the accept-bar mechanical audit is green. The standard ResNet branch stopped -- cgit v1.2.3