From 7ca9658999c8f882b3d5d295a4201cc9a1ce9cde Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 13:10:14 -0500 Subject: baseline: add convolutional hierarchical feedback alignment --- BASELINES.md | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'BASELINES.md') diff --git a/BASELINES.md b/BASELINES.md index 9c3a320..de7dfe8 100644 --- a/BASELINES.md +++ b/BASELINES.md @@ -15,6 +15,11 @@ weak in-house reimplementations from defining the state of the art. The audited implementations and completed results are in `RESULTS.md`: - BP, FA, and DFA share the SDIL forward architecture and data order; +- convolutional hierarchical FA (`hfa`) mirrors the ResNet residual DAG with + independent random 3x3 feedback tensors, exact parameter-free shortcut + adjoints, and local ReLU/BatchNorm Jacobians; it never copies or reads a + downstream forward convolution and is the mandatory baseline for any learned + hierarchical extension; - direct node perturbation uses a causal target on every hidden update and no learned vectorizer; - the no-traffic, `P=0` SDIL backbone is learned direct feedback by node -- cgit v1.2.3