Notice

This record has been edited as far as possible, missing data will be added when the version of record is issued.

Show simple item record

dc.contributor.author
Kassraie, Parnian
dc.contributor.author
Emmenegger, Nicolas
dc.contributor.author
Krause, Andreas
dc.contributor.author
Pacchiano, Aldo
dc.date.accessioned
2024-02-05T12:34:10Z
dc.date.available
2024-01-15T22:05:58Z
dc.date.available
2024-02-05T12:34:10Z
dc.date.issued
2023
dc.identifier.uri
http://hdl.handle.net/20.500.11850/652923
dc.description.abstract
Model selection in the context of bandit optimization is a challenging problem, as it requires balancing exploration and exploitation not only for action selection, but also for model selection. One natural approach is to rely on online learning algorithms that treat different models as experts. Existing methods, however, scale poorly (polyM) with the number of models M in terms of their regret. Our key insight is that, for model selection in linear bandits, we can emulate full-information feedback to the online learner with a favorable bias-variance trade-off. This allows us to develop ALEXP, which has an exponentially improved (log M) dependence on M for its regret. ALEXP has anytime guarantees on its regret, and neither requires knowledge of the horizon n, nor relies on an initial purely exploratory stage. Our approach utilizes a novel time-uniform analysis of the Lasso, establishing a new connection between online learning and high-dimensional statistics.
en_US
dc.language.iso
en
en_US
dc.title
Anytime Model Selection in Linear Bandits
en_US
dc.type
Conference Paper
ethz.book.title
Advances in Neural Information Processing Systems 36
en_US
ethz.size
37 p.
en_US
ethz.event
37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)
en_US
ethz.event.location
New Orleans, LA, USA
en_US
ethz.event.date
December 10-16, 2023
en_US
ethz.notes
Poster presented on December 13, 2023.
en_US
ethz.grant
Reliable Data-Driven Decision Making in Cyber-Physical Systems
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::03908 - Krause, Andreas / Krause, Andreas
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::03908 - Krause, Andreas / Krause, Andreas
en_US
ethz.identifier.url
https://neurips.cc/virtual/2023/poster/71280
ethz.grant.agreementno
815943
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
H2020
ethz.relation.continues
https://openreview.net/forum?id=YiRX7nQ77Q
ethz.date.deposited
2024-01-15T22:05:59Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.exportRequired
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Anytime%20Model%20Selection%20in%20Linear%20Bandits&rft.date=2023&rft.au=Kassraie,%20Parnian&Emmenegger,%20Nicolas&Krause,%20Andreas&Pacchiano,%20Aldo&rft.genre=proceeding&rft.btitle=Advances%20in%20Neural%20Information%20Processing%20Systems%2036
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record