English

Communication and Memory Efficient Testing of Discrete Distributions

Machine Learning 2019-06-12 v1 Data Structures and Algorithms Statistics Theory Machine Learning Statistics Theory

Abstract

We study distribution testing with communication and memory constraints in the following computational models: (1) The {\em one-pass streaming model} where the goal is to minimize the sample complexity of the protocol subject to a memory constraint, and (2) A {\em distributed model} where the data samples reside at multiple machines and the goal is to minimize the communication cost of the protocol. In both these models, we provide efficient algorithms for uniformity/identity testing (goodness of fit) and closeness testing (two sample testing). Moreover, we show nearly-tight lower bounds on (1) the sample complexity of any one-pass streaming tester for uniformity, subject to the memory constraint, and (2) the communication cost of any uniformity testing protocol, in a restricted `one-pass' model of communication.

Keywords

Cite

@article{arxiv.1906.04709,
  title  = {Communication and Memory Efficient Testing of Discrete Distributions},
  author = {Ilias Diakonikolas and Themis Gouleakis and Daniel M. Kane and Sankeerth Rao},
  journal= {arXiv preprint arXiv:1906.04709},
  year   = {2019}
}

Comments

Full version of COLT 2019 paper

R2 v1 2026-06-23T09:50:34.939Z