Fusion, propagation, and structuring in belief networks
Artificial Intelligence
Readings in uncertain reasoning
Readings in uncertain reasoning
COLT '90 Proceedings of the third annual workshop on Computational learning theory
Universal forecasting algorithms
Information and Computation
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
The weighted majority algorithm
Information and Computation
Simulating access to hidden information while learning
STOC '94 Proceedings of the twenty-sixth annual ACM symposium on Theory of computing
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Predicting a binary sequence almost as well as the optimal biased coin
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
On Bayes methods for on-line Boolean prediction
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
On-line prediction and conversion strategies
Machine Learning
Predicting Nearly As Well As the Best Pruning of a Decision Tree
Machine Learning - Special issue on the eighth annual conference on computational learning theory, (COLT '95)
Using and combining predictors that specialize
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
Derandomizing stochastic prediction strategies
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
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
Competitive on-line linear regression
NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
TIGHT WORST-CASE LOSS BOUNDS FOR PREDICTING WITH EXPERT ADVICE
TIGHT WORST-CASE LOSS BOUNDS FOR PREDICTING WITH EXPERT ADVICE
Universal portfolios with side information
IEEE Transactions on Information Theory
Probability theory for the Brier game
Theoretical Computer Science
Tracking a small set of experts by mixing past posteriors
The Journal of Machine Learning Research
IEEE Transactions on Signal Processing
Prediction With Expert Advice For The Brier Game
The Journal of Machine Learning Research
Universal randomized switching
IEEE Transactions on Signal Processing
Prediction with expert evaluators' advice
ALT'09 Proceedings of the 20th international conference on Algorithmic learning theory
Competitive online generalized linear regression under square loss
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III
Prediction with expert advice under discounted loss
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
The shortest path problem under partial monitoring
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Tracking the best of many experts
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Linear programming with online learning
Operations Research Letters
Online portfolio selection: A survey
ACM Computing Surveys (CSUR)
Hi-index | 0.01 |
In this paper we continue study of the games of predictionwith expert advice with uncountably many experts. A convenientinterpretation of such games is to construe the pool of experts asone “stochastic predictor”, who chooses one of theexperts in the pool at random according to the prior distribution onthe experts and then replicates the (deterministic )predictions of the chosen expert. We notice that if the stochasticpredictor‘s total loss is at most L with probability atleast p then the learner‘s loss can be bounded bycL + aln \frac{1}{p} for the usualconstants c and a. This interpretation is used torevamp known results and obtain new results on tracking the bestexpert. It is also applied to merging overconfident experts and tofitting polynomials to data.