Universal prediction of individual binary sequences in the presence of arbitrarily varying, memoryless additive noise

The problem of predicting the next outcome of an individual binary sequence, based on past observations which are corrupted by arbitrarily varying memoryless additive noise, is considered. The goal of the predictor is to perform, for each individual sequence, "almost" as well as the best in a set of experts, where performance is evaluated using a general loss function. This setting is a generalization of the original problem of universal prediction of individual sequences relative to a set of experts.