An Improved Uniform Convergence Bound with Fat-Shattering Dimension

作     者：Colomboni, Roberto Esposito, Emmanuel Paudice, Andrea 

作者机构：Department of Computer Science Università degli Studi di Milano Via Giovanni Celoria 18 Milan20131 Italy Computational Statistics and Machine Learning Istituto Italiano di Tecnologia Via Enrico Melen 83 Genoa16152 Italy 

出 版 物：《SSRN》 

年 卷 期：2023年

核心收录：

摘      要：The fat-shattering dimension characterizes the uniform convergence property of real-valued functions. The state-of-the-art upper bounds feature a multiplicative squared logarithmic factor on the sample complexity, leaving an open gap with the existing lower bound. We provide an improved uniform convergence bound that closes this gap. © 2023, The Authors. All rights reserved.