We analyze the regret, measured in terms of log loss, of the maximum likelihood (ML) sequential prediction strategy. This "follow the leader" strategy also defines one o...
This paper investigates some relations among four complexities of sequence over countably infinite alphabet, and shows that two kinds of empirical entropies and the self-entropy r...
We consider sequential regression of individual sequences under the square error loss. Using a competitive algorithm framework, we construct a sequential algorithm that can achieve...
We investigate label efficient prediction, a variant, proposed by Helmbold and Panizza, of the problem of prediction with expert advice. In this variant, the forecaster, after gues...
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...