Efficient Optimal Learning for Contextual Bandits

Friday, March 30, 2012 - 11:15am - 12:00pm
Keller 3-180
We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal regret. Our algorithm uses a cost sensitive classification learner as an oracle and has a running time polylog(N), where N is the number of classification rules among which the oracle might choose. This is exponentially faster than all previous algorithms that achieve optimal regret in this setting. Our formulation also enables us to create an algorithm with regret that is additive rather than multiplicative in feedback delay as in all
previous work.

Joint work with Miroslav Dudik, Daniel Hsu, Nikos Karampatziakis, John Langford, Lev Reyzin and Tong Zhang.
MSC Code: