STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
The weighted majority algorithm
Information and Computation
Universal portfolios with and without transaction costs
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Navigating nets: simple algorithms for proximity search
SODA '04 Proceedings of the fifteenth annual ACM-SIAM symposium on Discrete algorithms
Online convex optimization in the bandit setting: gradient descent without a gradient
SODA '05 Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms
Prediction, Learning, and Games
Prediction, Learning, and Games
Logarithmic regret algorithms for online convex optimization
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Universal portfolios with side information
IEEE Transactions on Information Theory
On the generalization ability of on-line learning algorithms
IEEE Transactions on Information Theory
SODA '10 Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms
Sharp dichotomies for regret minimization in metric spaces
SODA '10 Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms
Ranked bandits in metric spaces: learning diverse rankings over large document collections
The Journal of Machine Learning Research
| Hi-index | 0.00 |
The standard so-called experts algorithms are methods for utilizing a given set of "experts" to make good choices in a sequential decision-making problem. In the standard setting of experts algorithms, the decision maker chooses repeatedly in the same "state" based on information about how the different experts would have performed if chosen to be followed. In this paper we seek to extend this framework by introducing state information. More precisely, we extend the framework by allowing an experts algorithm to rely on state information, namely, partial information about the cost function, which is revealed to the decision maker before the latter chooses an action. This extension is very natural in prediction problems. For illustration, an experts algorithm, which is supposed to predict whether the next day will be rainy, can be extended to predicting the same given the current temperature. We introduce new algorithms, which attain optimal performance in the new framework, and apply to more general settings than variants of regression that have been considered in the statistics literature.