Conference item icon

Conference item

AdaGeo: Adaptive geometric learning for optimization and sampling

Abstract:

Gradient-based optimization and Markov Chain Monte Carlo sampling can be found at the heart of a multitude of machine learning methods. In high-dimensional settings, well-known issues such as slow-mixing, non-convexity and correlations can hinder the algorithms’ efficiency. In order to overcome these difficulties, we propose AdaGeo, a preconditioning framework for adaptively learning the geometry of parameter space during optimization or sampling. We use the Gaussian Process latent variable m...

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
Division:
MPLS Division
Department:
Engineering Science
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
Exeter College
Flaxman, S More by this author
More from this funder
Funding agency for:
Abbati, G
Publisher:
Proceedings of Machine Learning Research Publisher's website
Volume:
84
Pages:
226-234
Publication date:
2018-04-09
Acceptance date:
2017-12-22
ISSN:
1938-7228
Pubs id:
pubs:845063
URN:
uri:5e0c3640-183b-409d-a2df-d56fb8e3b8c1
UUID:
uuid:5e0c3640-183b-409d-a2df-d56fb8e3b8c1
Local pid:
pubs:845063

Terms of use


Metrics



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

TO TOP