From 39d1839ead0709798c2eb07104c3764ccf1ed3ae Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 14:30:04 -0500 Subject: results: pass reciprocal KP short gate --- RESULTS.md | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'RESULTS.md') diff --git a/RESULTS.md b/RESULTS.md index a4c63c9..76ffc29 100644 --- a/RESULTS.md +++ b/RESULTS.md @@ -868,6 +868,28 @@ so the single RRM-3 full validation run opens. The 9.86-point gap despite nearly perfect instantaneous alignment is retained as a negative diagnostic rather than treating cosine as a proxy for optimization equivalence. +### Modified Kolen--Pollack reciprocal baseline + +The independently implemented Akrout et al. reciprocal-plasticity baseline +uses the same local parent activity and child teaching field at corresponding +forward and feedback synapses, but each path recomputes its own correlation. +It never reads or copies a weight or weight-update tensor. Mechanics checks +give exactly zero direction, post-observation independence, and symmetric- +limit update errors. + +Its sole frozen 20-epoch full-development record passes every KP-1 gate: + +| method | validation accuracy | early alignment | train-period feedback cosine | estimated MACs | +|:--|--:|--:|--:|--:| +| KP | **82.66%** | 0.885583 | 0.854594 (epochs 11--20) | 1.4519e14 | +| BP at epoch 20 | 81.02% | n/a | exact by construction | 1.0949e14 | + +KP's final feedback/forward cosine is 0.901034. It uses zero task-loss queries, +costs `1.3261x` matched BP after explicitly charging the second reciprocal +correlation, and remains finite throughout the constant-LR screen. The result +opens the frozen KP-2 full baseline. It is entirely prior-art baseline evidence +and does not change the SDIL reviewer score. + ## 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