Pith. sign in

REVIEW 1 cited by

On implicit regularization: Morse functions and applications to matrix factorization

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 2001.04264 v2 pith:FDOKIJBJ submitted 2020-01-13 cs.LG stat.ML

classification cs.LGstat.ML
keywords implicitregularizationfactorizationfunctionsmatrixmorseapplicationsapply
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we revisit implicit regularization from the ground up using notions from dynamical systems and invariant subspaces of Morse functions. The key contributions are a new criterion for implicit regularization---a leading contender to explain the generalization power of deep models such as neural networks---and a general blueprint to study it. We apply these techniques to settle a conjecture on implicit regularization in matrix factorization.

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. Gradient Flow Equations for Deep Linear Neural Networks: A Survey from a Network Perspective

    cs.LG 2025-11 conditional novelty 6.0 of 10

    The adjacency-matrix reformulation of deep-linear gradient flow reveals a quotient-space structure of the loss landscape, but the proof that arcs between critical points determine stable and unstable manifolds is incomplete.

Pith tools