On the distribution-shift toy experiment, EGD reaches perfect generalization after only a few iterations and appears insensitive to initialization scale, whereas large initialization lengthens the vanilla-GD plateau and small initialization attenuates it. · CiteArk
Not assessedPlan blockedFindingc04-toy-egd-immediate-grokking
On the distribution-shift toy experiment, EGD reaches perfect generalization after only a few iterations and appears insensitive to initialization scale, whereas large initialization lengthens the vanilla-GD plateau and small initialization attenuates it.
Source: paper:PDF p. 6, Figure 6 and caption
Reported and observed measurements
No structured measurement is attached to this Claim.
Assessments (0)
No immutable Assessment has been published for this Claim yet.
