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
Not assessedPlan blockedFindingc06-main-sparse-parity-curves
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.
Source: paper:PDF pp. 3 and 9-10, Figure 3 and Section 5.1
Reported and observed measurements
No structured measurement is attached to this Claim.
Assessments (0)
No immutable Assessment has been published for this Claim yet.