Exponentiated strongly Rayleigh distributions

Mariet, Z; Sra, S; Jegelka, S

This is not the latest version of this item. The latest version can be found here.

Exponentiated strongly Rayleigh distributions

Download

Name

NeurIPS-2018-exponentiated-strongly-rayleigh-distributions-Paper.pdf

Description

Published version

Size

516.73 KB

Format

Adobe PDF

Checksum (MD5)

9608e5c8c793e4e3623cc50a2f277b42

sword-2020-12-21T19:19:52.original.xml (130 B)

Original SWORD entry document

Author(s)

Mariet, Z

•

Sra, S

•

Jegelka, S

Journal

Advances in Neural Information Processing Systems

Version

Final published version

Abstract

© 2018 Curran Associates Inc..All rights reserved. Strongly Rayleigh (SR) measures are discrete probability distributions over the subsets of a ground set. They enjoy strong negative dependence properties, as a result of which they assign higher probability to subsets of diverse elements. We introduce in this paper Exponentiated Strongly Rayleigh (ESR) measures, which sharpen (or smoothen) the negative dependence property of SR measures via a single parameter (the exponent) that can be intuitively understood as an inverse temperature. We develop efficient MCMC procedures for approximate sampling from ESRs, and obtain explicit mixing time bounds for two concrete instances: exponentiated versions of Determinantal Point Processes and Dual Volume Sampling. We illustrate some of the potential of ESRs, by applying them to a few machine learning problems; empirical results confirm that beyond their theoretical appeal, ESR-based models hold significant promise for these tasks.

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

https://hdl.handle.net/1721.1/132305

DOI of Published Version

https://papers.nips.cc/paper/2018/hash/1c6a0198177bfcc9bd93f6aab94aad3c-Abstract.html