AbstractThis paper resolves the problem of predicting as well as the best expert up to an additive term of the order o(n), where n is the length of a sequence of letters from a finite alphabet. We call the games that permit this weakly mixable and give a geometrical characterisation of the class of weakly mixable games. Weak mixability turns out to be equivalent to convexity of the finite part of the set of superpredictions. For bounded games we introduce the Weak Aggregating Algorithm that allows us to obtain additive terms of the form Cn
This thesis makes contributions to two problems in learning theory: prediction with expert advice an...
We consider the following problem. At each point of discrete time the learner must make a prediction...
AbstractThe paper applies the method of defensive forecasting, based on the use of game-theoretic su...
AbstractThis paper resolves the problem of predicting as well as the best expert up to an additive t...
AbstractWe consider the problem of learning to predict as well as the best in a group of experts mak...
AbstractWe consider the following problem. At each point of discrete time the learner must make a pr...
We study the fundamental problem of prediction with expert advice and develop regret lower bounds fo...
Mixability is a property of a loss which characterizes when constant regret is possible in the ga...
This paper formulates a protocol for prediction of packs, which is a special case of on-line predict...
This paper formulates a protocol for prediction of packs, which is a special case of on-line predict...
AbstractIn the first part of the paper we consider the problem of dynamically apportioning resources...
AbstractThe usual theory of prediction with expert advice does not differentiate between good and ba...
This thesis is devoted to on-line learning. An on-line learning algorithm receives elements of a seq...
The paper applies the method of defensive forecasting, based on the use of game-theoretic supermarti...
We provide several applications of Optimistic Mirror Descent, an online learning algorithm based on ...
This thesis makes contributions to two problems in learning theory: prediction with expert advice an...
We consider the following problem. At each point of discrete time the learner must make a prediction...
AbstractThe paper applies the method of defensive forecasting, based on the use of game-theoretic su...
AbstractThis paper resolves the problem of predicting as well as the best expert up to an additive t...
AbstractWe consider the problem of learning to predict as well as the best in a group of experts mak...
AbstractWe consider the following problem. At each point of discrete time the learner must make a pr...
We study the fundamental problem of prediction with expert advice and develop regret lower bounds fo...
Mixability is a property of a loss which characterizes when constant regret is possible in the ga...
This paper formulates a protocol for prediction of packs, which is a special case of on-line predict...
This paper formulates a protocol for prediction of packs, which is a special case of on-line predict...
AbstractIn the first part of the paper we consider the problem of dynamically apportioning resources...
AbstractThe usual theory of prediction with expert advice does not differentiate between good and ba...
This thesis is devoted to on-line learning. An on-line learning algorithm receives elements of a seq...
The paper applies the method of defensive forecasting, based on the use of game-theoretic supermarti...
We provide several applications of Optimistic Mirror Descent, an online learning algorithm based on ...
This thesis makes contributions to two problems in learning theory: prediction with expert advice an...
We consider the following problem. At each point of discrete time the learner must make a prediction...
AbstractThe paper applies the method of defensive forecasting, based on the use of game-theoretic su...