Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Consistency and fluctuations for stochastic gradient Langevin dynamics 

Tools
- Tools
+ Tools

Teh, Yee Whye, Thiery, Alexandre H. and Vollmer, Sebastian (2016) Consistency and fluctuations for stochastic gradient Langevin dynamics. Journal of Machine Learning Research, 17 . pp. 193-225. doi:10.5555/2946645.2946652 ISSN 1532-4435.

[img]
Preview
PDF
WRAP-consistency-fluctuations-stochastic-gradient-Langevin-dynamics-Vollmer-2016.pdf - Accepted Version - Requires a PDF viewer.

Download (1690Kb) | Preview
Official URL: http://dx.doi.org/10.5555/2946645.2946652

Request Changes to record.

Abstract

Applying standard Markov chain Monte Carlo (MCMC) algorithms to large data sets is computationally expensive. Both the calculation of the acceptance probability and the creation of informed proposals usually require an iteration through the whole data set. The recently proposed stochastic gradient Langevin dynamics (SGLD) method circumvents this problem by generating proposals which are only based on a subset of the data, by skipping the accept-reject step and by using decreasing step-sizes sequence (δm)m≥0.

We provide in this article a rigorous mathematical framework for analysing this algorithm. We prove that, under verifiable assumptions, the algorithm is consistent, satisfies a central limit theorem (CLT) and its asymptotic bias-variance decomposition can be characterized by an explicit functional of the step-sizes sequence (δm)m≥0. We leverage this analysis to give practical recommendations for the notoriously difficult tuning of this algorithm: it is asymptotically optimal to use a step-size sequence of the type δm = m-1/3, leading to an algorithm whose mean squared error (MSE) decreases at rate O(m-1/3).

Item Type: Journal Article
Subjects: Q Science > QA Mathematics
Divisions: Faculty of Science, Engineering and Medicine > Science > Mathematics
Library of Congress Subject Headings (LCSH): Markov processes, Monte Carlo method , Langevin equations , Stochastic differential equations , Big data
Journal or Publication Title: Journal of Machine Learning Research
Publisher: M I T Press
ISSN: 1532-4435
Official Date: 1 January 2016
Dates:
DateEvent
1 January 2016Published
1 June 2015Accepted
Volume: 17
Page Range: pp. 193-225
DOI: 10.5555/2946645.2946652
Status: Peer Reviewed
Publication Status: Published
Access rights to Published version: Restricted or Subscription Access
Date of first compliant deposit: 30 October 2019
Date of first compliant Open Access: 30 October 2019
RIOXX Funder/Project Grant:
Project/Grant IDRIOXX Funder NameFunder ID
EP/K009850/1 [EPSRC] Engineering and Physical Sciences Research Councilhttp://dx.doi.org/10.13039/501100000266
EP/K009362/1[EPSRC] Engineering and Physical Sciences Research Councilhttp://dx.doi.org/10.13039/501100000266
UNSPECIFIEDMinistry of Education - Singaporehttp://dx.doi.org/10.13039/501100001459
Related URLs:
  • Publisher

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us