English

Adaptive Sampling for Estimating Multiple Probability Distributions

Machine Learning 2019-12-10 v2 Machine Learning

Abstract

We consider the problem of allocating samples to a finite set of discrete distributions in order to learn them uniformly well in terms of four common distance measures: 22\ell_2^2, 1\ell_1, ff-divergence, and separation distance. To present a unified treatment of these distances, we first propose a general optimistic tracking algorithm and analyze its sample allocation performance w.r.t.~an oracle. We then instantiate this algorithm for the four distance measures and derive bounds on the regret of their resulting allocation schemes. We verify our theoretical findings through some experiments. Finally, we show that the techniques developed in the paper can be easily extended to the related setting of minimizing the average error (in terms of the four distances) in learning a set of distributions.

Keywords

Cite

@article{arxiv.1910.12406,
  title  = {Adaptive Sampling for Estimating Multiple Probability Distributions},
  author = {Shubhanshu Shekhar and Tara Javidi and Mohammad Ghavamzadeh},
  journal= {arXiv preprint arXiv:1910.12406},
  year   = {2019}
}

Comments

40 pages, 3 figures

R2 v1 2026-06-23T11:56:37.600Z