We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Improved second-order bounds for prediction with expert advice.
- Authors
Nicolò Cesa-Bianchi; Yishay Mansour; Gilles Stoltz
- Abstract
Abstract??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 second 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.
- Subjects
NUMERICAL analysis; FORECASTING; STATISTICS; MATHEMATICAL analysis
- Publication
Machine Learning, 2007, Vol 66, Issue 2-3, p321
- ISSN
0885-6125
- Publication type
Article
- DOI
10.1007/s10994-006-5001-7