The price of bandit information in multiclass online classification
published: Aug. 9, 2013, recorded: June 2013, views: 2950
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
We consider two scenarios of multiclass online learning of a hypothesis class H⊆YX. In the full information scenario, the learner is exposed to instances together with their labels. In the bandit scenario, the true label is not exposed, but rather an indication whether the learner’s prediction is correct or not. We show that the ratio between the error rates in the two scenarios is at most 8⋅|Y|⋅log(|Y|) in the realizable case, and O(√|Y|) in the agnostic case. The results are tight up to a logarithmic factor and essentially answer an open question from (Daniely et. al. - Multiclass learnability and the erm principle). We apply these results to the class of γ-margin multiclass linear classifiers in Rd. We show that the bandit error rate of this class is Θ(|Y|γ2) in the realizable case and Θ(1γ√|Y|T) in the agnostic case. This resolves an open question from (Kakade et. al. - Efficient bandit algorithms for onlinemulticlass prediction).
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !