most citedAdaptive Online Prediction by Following the Perturbed Leader

114 citations · 135 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG200515 cited

Universal Learning of Repeated Matrix Games

Jan Poland, Marcus Hutter

We study and compare the learning dynamics of two universal learning algorithms, one based on Bayesian learning and the other on prediction with expert advice. Both approaches have…

cs.LG20053 cited

FPL Analysis for Adaptive Bandits

Jan Poland

A main problem of "Follow the Perturbed Leader" strategies for online decision problems is that regret bounds are typically proven against oblivious adversary. In partial observati…

cs.LG2005

Defensive Universal Learning with Experts

Jan Poland, Marcus Hutter

This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedba…

cs.AI2005114 cited

Adaptive Online Prediction by Following the Perturbed Leader

Marcus Hutter, Jan Poland

When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the a…

cs.LG20051 cited

Master Algorithms for Active Experts Problems based on Increasing Loss Values

Jan Poland, Marcus Hutter

We specify an experts algorithm with the following characteristics: (a) it uses only feedback from the actions actually chosen (bandit setup), (b) it can be applied with countably…

cs.LG20042 cited

Prediction with Expert Advice by Following the Perturbed Leader for General Weights

Marcus Hutter, Jan Poland

When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the a…