In the first-order query model for zero-sum K× K matrix games,
playersob...
We provide a composite version of Ville's theorem that an event has zero...
We consider online convex optimization when a number k of data points ar...
We provide a new adaptive method for online convex optimization, MetaGra...
We revisit the classic regret-minimization problem in the stochastic
mul...
Conditional value-at-risk (CVaR) and value-at-risk (VaR) are popular
tai...
We study reward maximisation in a wide class of structured stochastic
mu...
We study Online Convex Optimization in the unbounded setting where neith...
Pure exploration (aka active testing) is the fundamental task of sequent...
We aim to design adaptive online learning algorithms that take advantage...
We determine the sample complexity of pure exploration bandit problems w...
We consider the online version of the isotonic regression problem. Given...
We aim to design strategies for sequential decision making that adjust t...
Follow-the-Leader (FTL) is an intuitive sequential prediction strategy t...
Most methods for decision-theoretic online learning are based on the Hed...