3 papers
cs.LG2008
A game-theoretic version of Oakes' example for randomized forecasting
Vladimir V. V'yugin
Using the game-theoretic framework for probability, Vovk and Shafer. have shown that it is always possible, using randomization, to make sequential probability forecasts that pass…
cs.LG2008
Prediction with Expert Advice in Games with Unbounded One-Step Gains
Vladimir V. V'yugin
The games of prediction with expert advice are considered in this paper. We present some modification of Kalai and Vempala algorithm of following the perturbed leader for the case…
cs.AI2008
On Sequences with Non-Learnable Subsequences
Vladimir V. V'yugin
The remarkable results of Foster and Vohra was a starting point for a series of papers which show that any sequence of outcomes can be learned (with no prior knowledge) using some…