COLT '90 Proceedings of the third annual workshop on Computational learning theory
The weighted majority algorithm
Information and Computation
Boosting a weak learning algorithm by majority
Information and Computation
On-line prediction and conversion strategies
Machine Learning
Exponentiated gradient versus gradient descent for linear predictors
Information and Computation
Journal of the ACM (JACM)
A decision-theoretic generalization of on-line learning and an application to boosting
Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Machine Learning - Special issue on context sensitivity and concept drift
EuroCOLT '99 Proceedings of the 4th European Conference on Computational Learning Theory
Gambling in a rigged casino: The adversarial multi-armed bandit problem
FOCS '95 Proceedings of the 36th Annual Symposium on Foundations of Computer Science
Sequential prediction of individual sequences under general loss functions
IEEE Transactions on Information Theory
Learning with Continuous Experts Using Drifting Games
ALT '08 Proceedings of the 19th international conference on Algorithmic Learning Theory
Learning with continuous experts using drifting games
Theoretical Computer Science
| Hi-index | 0.00 |
We consider the design of online master algorithms for combining the predictions from a set of experts where the absolute loss of the master is to be close to the absolute loss of the best expert. For the case when the master must produce binary predictions, the Binomial Weighting algorithm is known to be optimal when the number of experts is large. It has remained an open problem how to design master algorithms based on binomial weights when the predictions of the master are allowed to be real valued. In this paper we provide such an algorithm and call it the Binning algorithm because it maintains experts in an array of bins. We show that this algorithm is optimal in a relaxed setting in which we consider experts as continuous quantities. The algorithm is efficient and near-optimal in the standard experts setting.