Towards minimax policies for online linear optimization with bandit feedback

We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of order √ dn log N for any finite action set with N actions, under the assumption that the instan

• Type: Journal
• Year: 2012
• Where: CORR
• Authors: Sébastien Bubeck, Nicolò Cesa-Bianchi, Sham M. Kakade
• Keywords: CORR 2012, Education, Exponential Weights, Linear Optimization, Optimization Problem