Saved in:
Bibliographic Details
Main Author: Truong, Lan V.
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2208.04284
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915175896973312
author Truong, Lan V.
author_facet Truong, Lan V.
contents We show that the Rademacher complexity-based framework can establish non-vacuous generalization bounds for Convolutional Neural Networks (CNNs) in the context of classifying a small set of image classes. A key technical advancement is the formulation of novel contraction lemmas for high-dimensional mappings between vector spaces, specifically designed for general Lipschitz activation functions. These lemmas extend and refine the Talagrand contraction lemma across a broader range of scenarios. Our Rademacher complexity bound provides an enhancement over the results presented by Golowich et al. for ReLU-based Deep Neural Networks (DNNs). Moreover, while previous works utilizing Rademacher complexity have primarily focused on ReLU DNNs, our results generalize to a wider class of activation functions.
format Preprint
id arxiv_https___arxiv_org_abs_2208_04284
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle On Rademacher Complexity-based Generalization Bounds for Deep Learning
Truong, Lan V.
Machine Learning
We show that the Rademacher complexity-based framework can establish non-vacuous generalization bounds for Convolutional Neural Networks (CNNs) in the context of classifying a small set of image classes. A key technical advancement is the formulation of novel contraction lemmas for high-dimensional mappings between vector spaces, specifically designed for general Lipschitz activation functions. These lemmas extend and refine the Talagrand contraction lemma across a broader range of scenarios. Our Rademacher complexity bound provides an enhancement over the results presented by Golowich et al. for ReLU-based Deep Neural Networks (DNNs). Moreover, while previous works utilizing Rademacher complexity have primarily focused on ReLU DNNs, our results generalize to a wider class of activation functions.
title On Rademacher Complexity-based Generalization Bounds for Deep Learning
topic Machine Learning
url https://arxiv.org/abs/2208.04284