Salvato in:
Dettagli Bibliografici
Autori principali: Lindsey, Kathryn, Menon, Govind
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.01137
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912978183389184
author Lindsey, Kathryn
Menon, Govind
author_facet Lindsey, Kathryn
Menon, Govind
contents We use geometric invariant theory (GIT) to study the deep linear network (DLN). The Kempf-Ness theorem is used to establish that the $L^2$ regularizer is minimized on the balanced manifold. We introduce related balancing flows using the Riemannian geometry of fibers. The balancing flow defined by the $L^2$ regularizer is shown to converge to the balanced manifold at a uniform exponential rate. The balancing flow defined by the squared moment map is computed explicitly and shown to converge globally. This framework allows us to decompose the training dynamics into two distinct gradient flows: a regularizing flow on fibers and a learning flow on the balanced manifold. It also provides a common mathematical framework for balancedness in deep learning and linear systems theory. We use this framework to interpret balancedness in terms of fast-slow systems, model reduction and Bayesian principles.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01137
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Regularization Implies balancedness in the deep linear network
Lindsey, Kathryn
Menon, Govind
Machine Learning
Algebraic Geometry
Dynamical Systems
14L24, 37J15, 37C10, 68T07, 93B10, 53D20, 49J15, 37N40
We use geometric invariant theory (GIT) to study the deep linear network (DLN). The Kempf-Ness theorem is used to establish that the $L^2$ regularizer is minimized on the balanced manifold. We introduce related balancing flows using the Riemannian geometry of fibers. The balancing flow defined by the $L^2$ regularizer is shown to converge to the balanced manifold at a uniform exponential rate. The balancing flow defined by the squared moment map is computed explicitly and shown to converge globally. This framework allows us to decompose the training dynamics into two distinct gradient flows: a regularizing flow on fibers and a learning flow on the balanced manifold. It also provides a common mathematical framework for balancedness in deep learning and linear systems theory. We use this framework to interpret balancedness in terms of fast-slow systems, model reduction and Bayesian principles.
title Regularization Implies balancedness in the deep linear network
topic Machine Learning
Algebraic Geometry
Dynamical Systems
14L24, 37J15, 37C10, 68T07, 93B10, 53D20, 49J15, 37N40
url https://arxiv.org/abs/2511.01137