2006/02/27 by Nicolò Cesa‐Bianchi, Yishay Mansour, Cesa-Bianchi, Nicolo +3 · 5 citations
Decision Sciences · Computer Science · #Advanced Bandit Algorithms Research #Machine Learning and Algorithms #Gaussian Processes and Bayesian Inference
paper · pdf · doi:10.48550/arxiv.math/0602629
This work studies external regret in sequential prediction games with both positive and negative payoffs. External regret measures the difference between the payoff obtained by the forecasting strategy and the payoff of the best action. In this setting, we derive new and sharper regret bounds for the well-known exponentially weighted average forecaster and for a new forecaster with a different multiplicative update rule. Our analysis has two main advantages: first, no preliminary knowledge about the payoff sequence is needed, not even its range; second, our bounds are expressed in terms of sums of squared payoffs, replacing larger first-order quantities appearing in previous bounds. In addition, our most refined bounds have the natural and desirable property of being stable under rescalings and general translations of the payoff sequence.