Pith. sign in

REVIEW 1 cited by

Persistent Homology Captures the Generalization of Neural Networks Without A Validation Set

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 2106.00012 v1 pith:SUCWDLSC submitted 2021-05-31 cs.LG cs.AImath.AT

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

The training of neural networks is usually monitored with a validation (holdout) set to estimate the generalization of the model. This is done instead of measuring intrinsic properties of the model to determine whether it is learning appropriately. In this work, we suggest studying the training of neural networks with Algebraic Topology, specifically Persistent Homology (PH). Using simplicial complex representations of neural networks, we study the PH diagram distance evolution on the neural network learning process with different architectures and several datasets. Results show that the PH diagram distance between consecutive neural network states correlates with the validation accuracy, implying that the generalization error of a neural network could be intrinsically estimated without any holdout set.

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. A Quotient Homology Theory of Representation in Neural Networks

    cs.LG 2025-02 conditional novelty 7.0 of 10

    For ReLU networks, the homology of the output representation is isomorphic to the homology of the input manifold quotiented by the network's overlap decomposition, when polyhedron-manifold intersections are convex.

Pith tools