Generalization Error Bounds on Deep Learning with Markov DatasetsDownload PDF

Published: 31 Oct 2022, Last Modified: 11 Oct 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: Generalization Errors, Deep Learning, Bayesian Deep Learning
Abstract: In this paper, we derive upper bounds on generalization errors for deep neural networks with Markov datasets. These bounds are developed based on Koltchinskii and Panchenko's approach for bounding the generalization error of combined classifiers with i.i.d. datasets. The development of new symmetrization inequalities in high-dimensional probability for Markov chains is a key element in our extension, where the spectral gap of the infinitesimal generator of the Markov chain plays a key parameter in these inequalities. We also propose a simple method to convert these bounds and other similar ones in traditional deep learning and machine learning to Bayesian counterparts for both i.i.d. and Markov datasets. Extensions to $m$-order homogeneous Markov chains such as AR and ARMA models and mixtures of several Markov data services are given.
Supplementary Material: pdf
8 Replies

Loading