Pith. sign in

REVIEW 2 cited by

Understanding Grokking Through A Robustness Viewpoint

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.06597 v2 pith:H7TWAQSL submitted 2023-11-11 cs.LG cs.AI

classification cs.LGcs.AI
keywords grokkingrobustnessfindgeneralizationphenomenonadditioncommutativecondition
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Recently, an interesting phenomenon called grokking has gained much attention, where generalization occurs long after the models have initially overfitted the training data. We try to understand this seemingly strange phenomenon through the robustness of the neural network. From a robustness perspective, we show that the popular $l_2$ weight norm (metric) of the neural network is actually a sufficient condition for grokking. Based on the previous observations, we propose perturbation-based methods to speed up the generalization process. In addition, we examine the standard training process on the modulo addition dataset and find that it hardly learns other basic group operations before grokking, for example, the commutative law. Interestingly, the speed-up of generalization when using our proposed method can be explained by learning the commutative law, a necessary condition when the model groks on the test dataset. We also empirically find that $l_2$ norm correlates with grokking on the test data not in a timely way, we propose new metrics based on robustness and information theory and find that our new metrics correlate well with the grokking phenomenon and may be used to predict grokking.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Grokking vs. Learning: Same Features, Different Encodings

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Grokked and steadily trained models learn the same features, but steady training can produce much more compressible models in a parameter regime that grokking does not reach.

  2. GrokAlign: Geometric Characterisation and Acceleration of Grokking

    cs.LG 2025-06 conditional novelty 5.0 of 10

    GrokAlign, a Jacobian-norm regularizer, accelerates grokking by aligning Jacobians with training data, and centroid alignment tracks when generalization and robustness emerge.

Pith tools