Dr. Alekh Agarwal (Researcher Microsoft)
Efficient and Optimal Interactive Learning
Abstract: We present a new algorithm for the contextual bandit learning
problem, where the learner repeatedly takes one of K actions in response
to the observed context, and observes the reward only for that chosen
action. Our method assumes access to an oracle for solving fully supervised
cost-sensitive classification problems and achieves the statistically
optimal regret guarantee with only \tilde{O}(\sqrt{KT}) oracle calls
across all T rounds. By doing so, we obtain the most practical contextual
bandit learning algorithm amongst approaches that work for general policy
classes. We further conduct a proof-of-concept experiment which demonstrates
the excellent computational and prediction performance of (an online
variant of) our algorithm relative to several baselines.
[Joint work with Daniel Hsu, Satyen Kale, John Langford, Lihong Li
and Rob Schapire]
Dr. Kevin Patrick Murphy (Researcher Google)
Knowledge extraction from text, images and video
Abstract TBA.
Dr. Robert Bell (Researcher Google)
Lessons from the $1,000,000 Netflix Prize
Abstract: In October 2006, the DVD rental company Netflix released
more than 100 million user ratings of movies for a competition to predict
new ratings based on prior ratings. The size of the data (over 17,000
movies and 480,000 users) and the nature of human-movie interactions
produced many modeling challenges. One allure to data analysts around
the world was a $1,000,000 prize for a team achieving a ten percent
reduction in root mean squared prediction error relative to Netflix's
existing algorithm. Besides producing a photo finish worthy of a movie,
the 33-month competition spurred numerous advances in the science of
recommender systems and machine learning, more generally. After describing
some of the techniques used by the leaders, I will offer lessons and
raise some questions about building massive prediction models; the role
of statistics, computer science, and mathematics in such endeavors;
and prizes as a way to advance science. This is joint work with Chris
Volinsky and Yehuda Koren, former colleagues at AT&T Labs-Research.
