Pith. sign in

REVIEW 1 cited by

Controlling Grokking with Nonlinearity and Data Symmetry

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 2411.05353 v1 pith:OSXUHUYS submitted 2024-11-08 cs.LG cs.AI

classification cs.LGcs.AI
keywords layernonlinearityweightsentropygrokkingnetworkpatternsprojections
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper demonstrates that grokking behavior in modular arithmetic with a modulus P in a neural network can be controlled by modifying the profile of the activation function as well as the depth and width of the model. Plotting the even PCA projections of the weights of the last NN layer against their odd projections further yields patterns which become significantly more uniform when the nonlinearity is increased by incrementing the number of layers. These patterns can be employed to factor P when P is nonprime. Finally, a metric for the generalization ability of the network is inferred from the entropy of the layer weights while the degree of nonlinearity is related to correlations between the local entropy of the weights of the neurons in the final layer.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation

    cs.LG 2025-07 reject novelty 4.0 of 10

    The paper reports that dropout-based variance, embedding distribution shape, and neuron sparsity all shift around the moment a modular arithmetic network groks, and proposes these as forecasting signals.

Pith tools