Saved in:
Bibliographic Details
Main Author: Arjevani, Yossi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.14445
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916370114936832
author Arjevani, Yossi
author_facet Arjevani, Yossi
contents Critical points of an invariant function may or may not be symmetric. We prove, however, that if a symmetric critical point exists, those adjacent to it are generically symmetry breaking. This mathematical mechanism is shown to carry important implications for our ability to efficiently minimize invariant nonconvex functions, in particular those associated with neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2408_14445
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Symmetry & Critical Points
Arjevani, Yossi
Machine Learning
Numerical Analysis
Optimization and Control
Critical points of an invariant function may or may not be symmetric. We prove, however, that if a symmetric critical point exists, those adjacent to it are generically symmetry breaking. This mathematical mechanism is shown to carry important implications for our ability to efficiently minimize invariant nonconvex functions, in particular those associated with neural networks.
title Symmetry & Critical Points
topic Machine Learning
Numerical Analysis
Optimization and Control
url https://arxiv.org/abs/2408.14445