Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ziyin, Liu, Xu, Yizhou, Chuang, Isaac
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2408.15495
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915364630167552
author Ziyin, Liu
Xu, Yizhou
Chuang, Isaac
author_facet Ziyin, Liu
Xu, Yizhou
Chuang, Isaac
contents When symmetry is present in the loss function, the model is likely to be trapped in a low-capacity state that is sometimes known as a "collapse". Being trapped in these low-capacity states can be a major obstacle to training across many scenarios where deep learning technology is applied. We first prove two concrete mechanisms through which symmetries lead to reduced capacities and ignored features during training and inference. We then propose a simple and theoretically justified algorithm, syre, to remove almost all symmetry-induced low-capacity states in neural networks. When this type of entrapment is especially a concern, removing symmetries with the proposed method is shown to correlate well with improved optimization or performance. A remarkable merit of the proposed method is that it is model-agnostic and does not require any knowledge of the symmetry.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15495
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Remove Symmetries to Control Model Expressivity and Improve Optimization
Ziyin, Liu
Xu, Yizhou
Chuang, Isaac
Machine Learning
Artificial Intelligence
When symmetry is present in the loss function, the model is likely to be trapped in a low-capacity state that is sometimes known as a "collapse". Being trapped in these low-capacity states can be a major obstacle to training across many scenarios where deep learning technology is applied. We first prove two concrete mechanisms through which symmetries lead to reduced capacities and ignored features during training and inference. We then propose a simple and theoretically justified algorithm, syre, to remove almost all symmetry-induced low-capacity states in neural networks. When this type of entrapment is especially a concern, removing symmetries with the proposed method is shown to correlate well with improved optimization or performance. A remarkable merit of the proposed method is that it is model-agnostic and does not require any knowledge of the symmetry.
title Remove Symmetries to Control Model Expressivity and Improve Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.15495