Flexible modeling of diversity with strongly log-concave distributions

Robinson, J; Sra, S; Jegelka, S

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

Flexible modeling of diversity with strongly log-concave distributions

Download

Name

NeurIPS-2019-flexible-modeling-of-diversity-with-strongly-log-concave-distributions-Paper.pdf

Description

Published version

Size

345.62 KB

Format

Adobe PDF

Checksum (MD5)

afbef307888b137db47b0748397712e6

sword-2020-12-21T19:31:04.original.xml (130 B)

Original SWORD entry document

Author(s)

Robinson, J

•

Sra, S

•

Jegelka, S

Journal

Advances in Neural Information Processing Systems

Version

Final published version

Abstract

© 2019 Neural information processing systems foundation. All rights reserved. Strongly log-concave (SLC) distributions are a rich class of discrete probability distributions over subsets of some ground set. They are strictly more general than strongly Rayleigh (SR) distributions such as the well-known determinantal point process. While SR distributions offer elegant models of diversity, they lack an easy control over how they express diversity. We propose SLC as the right extension of SR that enables easier, more intuitive control over diversity, illustrating this via examples of practical importance. We develop two fundamental tools needed to apply SLC distributions to learning and inference: sampling and mode finding. For sampling we develop an MCMC sampler and give theoretical mixing time bounds. For mode finding, we establish a weak log-submodularity property for SLC functions and derive optimization guarantees for a distorted greedy algorithm.

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/1721.1/132308