A Sharp Lower Bound for Agnostic Learning with Sample Compression Schemes

Steve Hanneke, Aryeh Kontorovich

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We establish a tight characterization of the worst-case rates for the excess risk of agnostic learning with sample compression schemes and for uniform convergence for agnostic sample compression schemes. In particular, we find that the optimal rates of convergence for size-$k$ agnostic sample compression schemes are of the form $k n/k)n$, which contrasts with agnostic learning with classes of VC dimension $k$, where the optimal rates are of the form $kn$.
Original languageEnglish
Title of host publicationProceedings of the 30th International Conference on Algorithmic Learning Theory
EditorsAurélien Garivier, Satyen Kale
Place of PublicationChicago, Illinois
PublisherPMLR
Pages489-505
Number of pages17
Volume98
StatePublished - 1 Oct 2019

Fingerprint

Dive into the research topics of 'A Sharp Lower Bound for Agnostic Learning with Sample Compression Schemes'. Together they form a unique fingerprint.

Cite this