Hypothesis Set Stability and Generalization
Abstract
We present a study of generalization for data-dependent hypothesis sets. We give a general learning guarantee for data-dependent hypothesis sets based on a notion of transductive Rademacher complexity. Our main result is a generalization bound for data-dependent hypothesis sets expressed in terms of a notion of hypothesis set stability and a notion of Rademacher complexity for data-dependent hypothesis sets that we introduce. This bound admits as special cases both standard Rademacher complexity bounds and algorithm-dependent uniform stability bounds. We also illustrate the use of these learning bounds in the analysis of several scenarios.
Keywords
Cite
@article{arxiv.1904.04755,
title = {Hypothesis Set Stability and Generalization},
author = {Dylan J. Foster and Spencer Greenberg and Satyen Kale and Haipeng Luo and Mehryar Mohri and Karthik Sridharan},
journal= {arXiv preprint arXiv:1904.04755},
year = {2020}
}
Comments
Published in NeurIPS 2019. This version is equivalent to the camera-ready version but also includes the supplementary material