Papers › Implicit Regularization via Neural Feature Alignment

Implicit Regularization via Neural Feature Alignment

3 Aug 2020NeurIPS Workshop DL-IG 2020 12arXiv:2008.00938archive 2025-07-28

Aristide Baratin, Thomas George, César Laurent, R. Devon Hjelm, Guillaume Lajoie, Pascal Vincent, Simon Lacoste-Julien

We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a regularization effect induced by a dynamical alignment of the neural tangent features introduced by Jacot et al, along a small number of task-relevant directions. This can be interpreted as a combined mechanism of feature selection and compression. By extrapolating a new analysis of Rademacher complexity bounds for linear models, we motivate and study a heuristic complexity measure that captures this phenomenon, in terms of sequences of tangent kernel classes along optimization paths.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tfjgeorge/ntk_alignment officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Model Compressionfeature selection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Feature Selection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections