A Competitive Algorithm for Agnostic Active Learning

arXiv:2310.18786 · cs.LG, cs.DS · Submitted 2023-10-28 · Read on arXiv

cs.LG, cs.DS

Submitted: 2023-10-28

Updated: 2026-10-27

License: http://creativecommons.org/publicdomain/zero/1.0/

The gist: For some hypothesis classes and input distributions, active agnostic learning needs exponentially fewer samples than passive learning; for other classes and distributions…

Terminology

Abstract

For some hypothesis classes and input distributions, active agnostic learning needs exponentially fewer samples than passive learning; for other classes and distributions, it offers little to no improvement. The most popular algorithms for agnostic active learning express their performance in terms of a parameter called the disagreement coefficient, but it is known that these algorithms are inefficient on some inputs. We take a different approach to agnostic active learning, getting an algorithm that is competitive with the optimal algorithm for any binary hypothesis class H and distribution D X over X. In particular, if any algorithm can use m* queries to get O(η) error, then our algorithm uses O(m* H) queries to get O(η) error. Our algorithm lies in the vein of the splitting-based approach of Dasgupta [2004], which gets a similar result for the realizable (η= 0) setting. We also show that it is NP-hard to do better than our algorithm's O(H) overhead in general.

Sources

Related papers