From 901315d2c141d44c716395bc97568268c23b6639 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Thu, 30 Jul 2026 16:39:35 -0500 Subject: figure: add audited plain CNN Pareto frontier --- results/figs/figure7_plain_cnn_pareto_caption.md | 1 + 1 file changed, 1 insertion(+) create mode 100644 results/figs/figure7_plain_cnn_pareto_caption.md (limited to 'results/figs/figure7_plain_cnn_pareto_caption.md') diff --git a/results/figs/figure7_plain_cnn_pareto_caption.md b/results/figs/figure7_plain_cnn_pareto_caption.md new file mode 100644 index 0000000..eadd929 --- /dev/null +++ b/results/figs/figure7_plain_cnn_pareto_caption.md @@ -0,0 +1 @@ +**Figure 7: Complete matched Plain-CNN accuracy–time crossover.** Best CIFAR-10 validation accuracy is plotted against measured single-GPU GTX-1080 training wall time for every registered method at miniCNN, VGGlike, and VGG16. Solid lines are empirical Pareto frontiers among non-backpropagation methods; dashed lines include BP as an optimization reference. Crosses retain nonfinite trajectories at their last finite validation metric. SDIL lies on the local-method frontier for miniCNN and VGGlike, while clean KP slightly dominates it at VGG16. Dual Propagation remains more accurate than SDIL at VGG16 but requires substantially more wall time. The figure supports local-method scaling and cost competitiveness, not global dominance over BP. -- cgit v1.2.3