New Statistical and Computational Results for Learning Junta Distributions

International Workshop and International Workshop on Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM), 2025

9 May 2025

Lorenzo Beretta

ArXiv (abs)PDF HTML Github

Main:21 Pages

2 Figures

Bibliography:3 Pages

1 Tables

Abstract

We study the problem of learning junta distributions on $\{0, 1\}^n$ , where a distribution is a $k$ -junta if its probability mass function depends on a subset of at most $k$ variables. We make two main contributions:

View on arXiv

Comments on this paper