Across Parity(n,k) settings (400,2), (100,3), and (50,4), EGD groks substantially earlier—typically after only a few epochs—while vanilla SGD has a long test-accuracy plateau before eventually grokking. · CiteArk
Across Parity(n,k) settings (400,2), (100,3), and (50,4), EGD groks substantially earlier—typically after only a few epochs—while vanilla SGD has a long test-accuracy plateau before eventually grokking.
来源:paper:PDF pp. 3 and 9-10, Figure 3 and Section 5.1