From 13cb2f40c600a7e6fa0918c234ee9293b46bb34c Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Tue, 21 Jul 2026 15:11:41 -0500 Subject: figures: disclose EP evaluation state initialization --- experiments/plot_main_figures.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'experiments/plot_main_figures.py') diff --git a/experiments/plot_main_figures.py b/experiments/plot_main_figures.py index 9f719d9..19d3819 100644 --- a/experiments/plot_main_figures.py +++ b/experiments/plot_main_figures.py @@ -574,7 +574,9 @@ BP is a nonlocal reference and is excluded from frontier construction. Labels gi Within each matched architecture, every method uses the same budget: 25 epochs for d1 and 60 epochs for d2. EP retains its published raw-pixel, hard-sigmoid energy dynamics and relaxation schedule; SDIL retains its z-scored, tanh feedforward dynamics. Thus architecture, examples, and -epochs are matched, but preprocessing and state dynamics are intentionally method-native. +epochs are matched, but preprocessing and state dynamics are intentionally method-native. EP +training particles persist across presentations as published; test particles are freshly +zero-initialized and run for the full free-phase schedule at each evaluation. **Figure 2 | Credit-assignment scaling in deep local-learning networks.** Mean ± sample standard deviation across five seeds on the same CIFAR-10 width-64 residual MLP protocol. **a,** Test -- cgit v1.2.3