This 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 C √ n.

This paper compares two methods of prediction with expert advice, the Aggregating Algorithm and the Defensive Forecasting, in two different settings. The first setting is traditional, with a countable number of experts and a finite number of outcomes. Surprisingly, these two methods of fundamentally different origin lead to identical procedures. In the second setting the experts can give advice conditional on the learner’s future decision. Both methods can be used in the new setting and give the same performance guarantees as in the traditional setting. However, whereas defensive forecasting can be applied directly, the AA requires substantial modifications

No abstract

Abstract. This paper resolves the problem of predicting as well as the best expert up to an additive term o(n), where n is the length of a sequence of letters from a finite alphabet. For the bounded games the paper introduces the Weak Aggregating Algorithm that allows us to obtain additive terms of the form C √ n. A modification of the Weak Aggregating Algorithm that covers unbounded games is also described.

No abstract