Conference item icon

Conference item

Online optimization of smoothed piecewise constant functions

Abstract:

We study online optimization of smoothed piecewise constant functions over the domain [0, 1). This is motivated by the problem of adaptively picking parameters of learning algorithms as in the recently introduced framework by Gupta and Roughgarden (2016). Majority of the machine learning literature has focused on Lipschitz-continuous functions or functions with bounded gradients.1 This is with good reason—any learning algorithm suffers linear regret even against piecewise constant functions t...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
  • (Accepted manuscript, pdf, 480.8KB)

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
Publisher:
Proceedings of Machine Learning Research Publisher's website
Host title:
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics
Series:
Proceedings of Machine Learning Research
Volume:
54
Pages:
412-420
Publication date:
2017-01-01
Acceptance date:
2017-01-24
ISSN:
1938-7228
Pubs id:
pubs:673197
UUID:
uuid:8e50e930-b696-4fde-9597-6d471e7d5515
Local pid:
pubs:673197
Source identifiers:
673197
Deposit date:
2017-01-26

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