[Ml-stat-talks] Fwd: Wilks Statistics Seminar: Daniel Hsu, Today, April 22 @ 12:30pm, Sherrerd Hall 101
bee at princeton.edu
Fri Apr 22 11:52:54 EDT 2016
Talk of interest today.
---------- Forwarded message ----------
*** Wilks Statistics Seminar ***
DATE: Today, April 22, 2016
LOCATION: Sherrerd Hall 101
SPEAKER: Daniel Hsu, Columbia University
TITLE: Reducing Contextual Bandits to Supervised Learning
ABSTRACT: I'll describe a fast and simple algorithm for the contextual
bandit learning problem, where the learner repeatedly takes an action in
response to the observed context, observing the reward only for that
action. The algorithm assumes access to an oracle for solving
cost-sensitive classification problems and achieves the statistically
optimal regret guarantee with only O ~ (T √ ) O~(T) oracle calls across
all T T rounds.
Joint work with Alekh Agarwal, Satyen Kale, John Langford, Lihong Li, and
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Ml-stat-talks