Inference under Information Constraints II: Communication Constraints and Shared Randomness

05/20/2019
by   Jayadev Acharya, et al.
0

A central server needs to perform statistical inference based on samples that are distributed over multiple users who can each send a message of limited length to the center. We study problems of distribution learning and identity testing in this distributed inference setting and examine the role of shared randomness as a resource. We propose a general-purpose simulate-and-infer strategy that uses only private-coin communication protocols and is sample-optimal for distribution learning. This general strategy turns out to be sample-optimal even for distribution testing among private-coin protocols. Interestingly, we propose a public-coin protocol that outperforms simulate-and-infer for distribution testing and is, in fact, sample-optimal. Underlying our public-coin protocol is a random hash that when applied to the samples minimally contracts the chi-squared distance of their distribution to the uniform distribution.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/20/2021

Inference under Information Constraints III: Local Privacy Constraints

We study goodness-of-fit and independence testing of discrete distributi...
research
04/19/2018

Distributed Simulation and Distributed Inference

Independent samples from an unknown probability distribution p on a doma...
research
07/20/2019

Domain Compression and its Application to Randomness-Optimal Distributed Goodness-of-Fit

We study goodness-of-fit of discrete distributions in the distributed se...
research
12/30/2018

Inference under Information Constraints I: Lower Bounds from Chi-Square Contraction

We consider a distributed inference problem where only limited informati...
research
08/04/2023

LISA: LIghtweight single-server Secure Aggregation with a public source of randomness

Secure Aggregation (SA) is a key component of privacy-friendly federated...
research
02/02/2022

Optimal high-dimensional and nonparametric distributed testing under communication constraints

We derive minimax testing errors in a distributed framework where the da...
research
03/01/2022

Addressing Randomness in Evaluation Protocols for Out-of-Distribution Detection

Deep Neural Networks for classification behave unpredictably when confro...

Please sign up or login with your details

Forgot password? Click here to reset