Learning in the presence of malicious errors
SIAM Journal on Computing
The weighted majority algorithm
Information and Computation
On-line prediction and conversion strategies
Euro-COLT '93 Proceedings of the first European conference on Computational learning theory
Journal of the ACM (JACM)
A game of prediction with expert advice
Journal of Computer and System Sciences - Special issue on the eighth annual workshop on computational learning theory, July 5–8, 1995
Minimax regret under log loss for general classes of experts
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
Tight worst-case loss bounds for predicting with expert advice
EuroCOLT '95 Proceedings of the Second 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
Using upper confidence bounds for online learning
FOCS '00 Proceedings of the 41st Annual Symposium on Foundations of Computer Science
Optimization problems in congestion control
FOCS '00 Proceedings of the 41st Annual Symposium on Foundations of Computer Science
Sequential prediction of individual sequences under general loss functions
IEEE Transactions on Information Theory
Universal prediction of individual binary sequences in the presence of noise
IEEE Transactions on Information Theory
Computer Networks: The International Journal of Computer and Telecommunications Networking
Toward a classification of finite partial-monitoring games
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
Improved second-order bounds for prediction with expert advice
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Partial monitoring with side information
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
Toward a classification of finite partial-monitoring games
Theoretical Computer Science
| Hi-index | 0.00 |
We investigate the problem of predicting a sequence when the information about the previous elements (feedback) is onlypartial and possiblydep endent on the predicted values. This setting can be seen as a generalization of the classical multi-armed bandit problem and accommodates as a special case a natural bandwidth allocation problem. According to the approach adopted byman yauthors, we give up any statistical assumption on the sequence to be predicted. We evaluate the performance against the best constant predictor (regret), as it is common in iterated game analysis. We show that for anydiscrete loss function and feedback function only one of two situations can occur: either there is a prediction strategythat achieves in T rounds a regret of at most O(T3/4(ln T)1/2) or there is a sequence which cannot be predicted byan yalgorithm without incurring a regret of Ω(T). We prove both sides constructively, that is when the loss and feedback functions satisfya certain condition, we present an algorithm that generates predictions with the claimed performance; otherwise we show a sequence that no algorithm can predict without incurring a linear regret with probabilityat least 1/2.