cs.LGNov 18, 2026

Near-Quadratic Sample Compression for All VC Classes

Authors: Yang Cai, Vineet Gupta, Yanchen Jiang, Christopher Liaw, Aranyak Mehta, Shay Moran, Grigoris Velegkas, Di Wang, 

Organizations: Google · Yale University · the Technion

Abstract

The sample compression conjecture is a longstanding open problem in learning theory, originating in the work of Littlestone and Warmuth in the 1980s. At its heart is a connection between simplification and generalization: if a predictor consistent with a training sample is defined using only a small part of that sample, then it is likely to generalize. Sample compression schemes formalize this idea, and many natural learning algorithms can be analyzed this way. The sample compression conjecture of Floyd and Warmuth (1995) asserts that every binary concept class of VC dimension dd admits a sample compression scheme of size O(d)O(d); a weaker conjecture asks only for size polynomial in dd. Both have remained open: the first bound depending only on dd, due to Moran and Yehudayoff (2016), is exponential in dd. We prove the weaker conjecture by constructing a sample compression scheme of size O(d2log⁡2d)O(d^2 \log^2 d).

Figures & tables

Explore similar work

CardsList
  1. High-arity Sample Compression

    May 12, 2026Leonardo N. Coregliano, William OpichSample CompressionPAC Learning

  2. What is Learnable in Valiant's Theory of the Learnable?

    May 13, 2026Steve Hanneke, Anay Mehrotra, Grigoris Velegkas +1Sample CompressionHalfspace Learning

  3. Uniform convergence at optimal rate and scale

    Oct 17, 2026Noga Alon, Steve Hanneke, Shay Moran +1Generalization Bounds