Back to Explorer
Research PaperResearchia:202602.14024[Artificial Intelligence > AI]

On the implicit regularization of Langevin dynamics with projected noise

Govind Menon

Abstract

We study Langevin dynamics with noise projected onto the directions orthogonal to an isometric group action. This mathematical model is introduced to shed new light on the effects of symmetry on stochastic gradient descent for over-parametrized models. Our main result identifies a novel form of implicit regularization: when the initial and target density are both invariant under the group action, Langevin dynamics with projected noise is equivalent in law to Langevin dynamics with isotropic diffusion but with an additional drift term proportional to the negative log volume of the group orbit. We prove this result by constructing a coupling of the two processes via a third process on the group itself, and identify the additional drift as the mean curvature of the orbits.


Source: arXiv:2602.12257v1 - http://arxiv.org/abs/2602.12257v1 PDF: https://arxiv.org/pdf/2602.12257v1 Original Link: http://arxiv.org/abs/2602.12257v1

Submission:2/14/2026
Comments:0 comments
Subjects:AI; Artificial Intelligence
Original Source:
View Original PDF
arXiv: This paper is hosted on arXiv, an open-access repository
Was this helpful?

Discussion (0)

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

On the implicit regularization of Langevin dynamics with projected noise | Researchia | Researchia