A Generalization Bound for a Family of Implicit Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fung, Samy Wu, Berkels, Benjamin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908812258050048
author Fung, Samy Wu
Berkels, Benjamin
author_facet Fung, Samy Wu
Berkels, Benjamin
contents Implicit networks are a class of neural networks whose outputs are defined by the fixed point of a parameterized operator. They have enjoyed success in many applications including natural language processing, image processing, and numerous other applications. While they have found abundant empirical success, theoretical work on its generalization is still under-explored. In this work, we consider a large family of implicit networks defined parameterized contractive fixed point operators. We show a generalization bound for this class based on a covering number argument for the Rademacher complexity of these architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07427
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Generalization Bound for a Family of Implicit Networks
Fung, Samy Wu
Berkels, Benjamin
Machine Learning
68T07 68T07 68T07 68T07 68T07 68T07
Implicit networks are a class of neural networks whose outputs are defined by the fixed point of a parameterized operator. They have enjoyed success in many applications including natural language processing, image processing, and numerous other applications. While they have found abundant empirical success, theoretical work on its generalization is still under-explored. In this work, we consider a large family of implicit networks defined parameterized contractive fixed point operators. We show a generalization bound for this class based on a covering number argument for the Rademacher complexity of these architectures.
title A Generalization Bound for a Family of Implicit Networks
topic Machine Learning
68T07 68T07 68T07 68T07 68T07 68T07
url https://arxiv.org/abs/2410.07427