18 citations · 20 across the 3 of their papers we have counts for
3 papers
cs.LG2005★ 18 cited
Competitive on-line learning with a convex loss function
Vladimir Vovk
We consider the problem of sequential decision making under uncertainty in which the loss caused by a decision depends on the following binary observation. In competitive on-line l…
cs.LG2005★ 1 cited
Defensive forecasting for linear protocols
Vladimir Vovk, Ilia Nouretdinov, Akimichi Takemura +1
We consider a general class of forecasting protocols, called "linear protocols", and discuss several important special cases, including multi-class forecasting. Forecasting is form…
cs.LG2005★ 1 cited
Defensive forecasting
Vladimir Vovk, Akimichi Takemura, Glenn Shafer
We consider how to make probability forecasts of binary labels. Our main mathematical result is that for any continuous gambling strategy used for detecting disagreement between th…