Journal article icon

Journal article

Consistency and fluctuations for stochastic gradient Langevin dynamics

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 s...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Publisher's version

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Department:
Oxford, MPLS, Statistics
Role:
Author
More by this author
Institution:
University of Oxford
Department:
Oxford, MPLS, Statistics
Role:
Author
More from this funder
Grant:
EP/K009850/1, EP/N000188/1 and EP/K009362/1
Publisher:
Journal of Machine Learning Research Publisher's website
Journal:
Journal of Machine Learning Research Journal website
Volume:
17
Pages:
1-33
Publication date:
2016-01-01
ISSN:
1532-4435
URN:
uuid:901ca27e-11e3-4b73-bbe6-4f791c4b7734
Source identifiers:
612564
Local pid:
pubs:612564

Terms of use


Metrics


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP