Optimal Multi-Distribution Learning

TL;DR

This paper introduces a new algorithm for multi-distribution learning that achieves near-optimal sample complexity, addressing key open problems and extending to Rademacher classes, with implications for robustness and fairness.

Contribution

The paper presents a novel, oracle-efficient algorithm for MDL that matches lower bounds and extends to Rademacher classes, resolving open problems in the field.

Findings

Achieves sample complexity of (d+k)/ε^2, matching lower bounds.

Establishes the necessity of randomization in MDL.

Extends results to Rademacher classes.

Abstract

Multi-distribution learning (MDL), which seeks to learn a shared model that minimizes the worst-case risk across $k$ distinct data distributions, has emerged as a unified framework in response to the evolving demand for robustness, fairness, multi-group collaboration, etc. Achieving data-efficient MDL necessitates adaptive sampling, also called on-demand sampling, throughout the learning process. However, there exist substantial gaps between the state-of-the-art upper and lower bounds on the optimal sample complexity. Focusing on a hypothesis class of Vapnik-Chervonenkis (VC) dimension d, we propose a novel algorithm that yields an varepsilon-optimal randomized hypothesis with a sample complexity on the order of (d+k)/varepsilon^2 (modulo some logarithmic factor), matching the best-known lower bound. Our algorithmic ideas and theory are further extended to accommodate Rademacher classes. The proposed algorithms are oracle-efficient, which access the hypothesis class solely through an empirical risk minimization oracle. Additionally, we establish the necessity of randomization, revealing a large sample size barrier when only deterministic hypotheses are permitted. These findings resolve three open problems presented in COLT 2023 (i.e., citet[Problems 1, 3 and 4]{awasthi2023sample}).