论文信息 - Multiarmed Bandits With Limited Expert Advice

Multiarmed Bandits With Limited Expert Advice

We consider the problem of minimizing regret in the setting of advice-efficient multiarmed bandits with expert advice. We give an algorithm for the setting of K arms and N experts out of which we are allowed to query and use only M experts’ advice in each round, which has a regret bound 1 of ~ O q minfK;MgN M T after T rounds. We also prove that any algorithm for this problem must have expected regret at least ~ q minfK;MgN M T , thus showing that our upper bound is nearly tight. This solves the COLT 2013 open problem of Seldin et al. (2013).

Satyen Kale | Satyen Kale

[1] Manfred K. Warmuth,et al. The Weighted Majority Algorithm , 1994, Inf. Comput..

[2] Sanjeev Arora,et al. The Multiplicative Weights Update Method: a Meta-Algorithm and Applications , 2012, Theory Comput..

[3] Koby Crammer,et al. Open Problem: Adversarial Multiarmed Bandits with Limited Advice , 2013, COLT.

[4] Koby Crammer,et al. Prediction with Limited Advice and Multiarmed Bandits with Paid Observations , 2014, ICML.

[5] Jean-Yves Audibert,et al. Regret Bounds and Minimax Policies under Partial Monitoring , 2010, J. Mach. Learn. Res..

[6] Martin Raab,et al. "Balls into Bins" - A Simple and Tight Analysis , 1998, RANDOM.

[7] Peter Auer,et al. The Nonstochastic Multiarmed Bandit Problem , 2002, SIAM J. Comput..

[8] Gábor Lugosi,et al. Minimax Policies for Combinatorial Prediction Games , 2011, COLT.