Journal article icon

Journal article

MEMe: An accurate maximum entropy method for efficient approximations in large-scale machine learning

Abstract:
Efficient approximation lies at the heart of large-scale machine learning problems. In this paper, we propose a novel, robust maximum entropy algorithm, which is capable of dealing with hundreds of moments and allows for computationally efficient approximations. We showcase the usefulness of the proposed method, its equivalence to constrained Bayesian variational inference and demonstrate its superiority over existing approaches in two applications, namely, fast log determinant estimation and information-theoretic Bayesian optimisation.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.3390/e21060551

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0002-1143-9786
Publisher:
MDPI
Journal:
Entropy More from this journal
Volume:
21
Issue:
6
Article number:
551
Publication date:
2019-05-31
Acceptance date:
2019-05-29
DOI:
EISSN:
1099-4300
Keywords:
Pubs id:
pubs:1011734
UUID:
uuid:0ae5769d-2cc1-4ddb-aeb8-f7e2549fad2b
Local pid:
pubs:1011734
Source identifiers:
1011734
Deposit date:
2019-10-26

Terms of use


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