Work

Hypothesis Set Stability and Generalization

Year: 2019

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1904.04755

Authors: Foster, Dylan J., Greenberg, Spencer, Kale, Satyen, Luo, Haipeng, Mohri, Mehryar, Sridharan, Karthik

Institutions: Massachusetts Institute of Technology, Alphabet (United States), University of Southern California, Google (United States), Cornell University

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2937266646

Cites: 43

Cited by: 13

Related to: 10