Optimal testing for properties of distributions
Name
optimal-testing-for-properties-of-distributions.pdf
Size
440.58 KB
Format
Adobe PDF
Checksum (MD5)
a64ba7d8fe7108148c1a6b06e6f98ae1
Author(s)
Acharya, Jayadev
Daskalakis, Konstantinos
Kamath, Gautam Chetan
Date Issued
December 2015
Journal
Advances in Neural Information Processing Systems 28 (NIPS 2015)
Publisher
Neural Information Processing Systems Foundation
Citation
Acharya, Jayadev, Constantinos Daskalakis, and Gautam Kamath. "Optimal Testing for Properties of Distributions." Advances in Neural Information Processing Systems 28 (NIPS 2015), Montreal, Canada, 7-12 December, 2015. NIPS 2015.
Version
Final published version
Abstract
Given samples from an unknown discrete distribution p, is it possible to distinguish whether p belongs to some class of distributions C versus p being far from every distribution in C? This fundamental question has received tremendous attention in statistics, focusing primarily on asymptotic analysis, as well as in information theory and theoretical computer science, where the emphasis has been on small sample size and computational complexity. Nevertheless, even for basic properties of discrete distributions such as monotonicity, independence, logconcavity, unimodality, and monotone-hazard rate, the optimal sample complexity
is unknown. We provide a general approach via which we obtain sample-optimal and computationally efficient testers for all these distribution families. At the core of our approach is an algorithm which solves the following problem: Given samples from an unknown distribution p, and a known distribution q, are p and q close in x[superscript 2]-distance, or far in total variation distance? The optimality of our testers is established by providing matching lower bounds, up to constant factors. Finally, a necessary building block for our testers and an important byproduct of our work are the first known computationally efficient proper learners for discrete log-concave, monotone hazard rate distributions.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/5839-optimal-testing-for-properties-of-distributions
