For modular addition at each reported modulus (79, 97, and 127), EGD reaches high test accuracy after only a few epochs, vanilla SGD remains on a long plateau before eventually grokking, and column normalization also groks faster than vanilla SGD. · CiteArk
Not assessedPlan blockedFindingc07-main-modular-addition-curves
For modular addition at each reported modulus (79, 97, and 127), EGD reaches high test accuracy after only a few epochs, vanilla SGD remains on a long plateau before eventually grokking, and column normalization also groks faster than vanilla SGD.
Source: paper:PDF pp. 2 and 10, Figure 1 and Section 5.2
Reported and observed measurements
No structured measurement is attached to this Claim.
Assessments (0)
No immutable Assessment has been published for this Claim yet.
