Journal of the ACM (JACM)
Online computation and competitive analysis
Online computation and competitive analysis
Machine Learning - Special issue on context sensitivity and concept drift
Derandomizing Stochastic Prediction Strategies
Machine Learning - Special issue: computational learning theory, COLT '97
On-line Learning and the Metrical Task System Problem
Machine Learning
Developments from a June 1996 seminar on Online algorithms: the state of the art
Developments from a June 1996 seminar on Online algorithms: the state of the art
Linear programming with online learning
Operations Research Letters
Robust solutions of uncertain linear programs
Operations Research Letters
Linear programming with online learning
Operations Research Letters
Hi-index | 0.00 |
We propose online decision strategies for time-dependent sequences of linear programs which use no distributional and minimal geometric assumptions about the data. These strategies are obtained through Vovk's aggregating algorithm which combines recommendations from a given strategy pool. We establish an average-performance bound for the resulting solution sequence.