#### Filter Results:

#### Publication Year

2002

2015

#### Publication Type

#### Co-author

#### Publication Venue

#### Key Phrases

Learn More

We apply the method of defensive forecasting, based on the use of game-theoretic supermartingales, to prediction with expert advice. In the traditional setting of a countable number of experts and a finite number of outcomes, the Defensive Forecasting Algorithm is very close to the well-known Aggregating Algorithm. Not only the performance guarantees but… (More)

In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal-Hedge bound, which mainly depends on the effective number of experts but also weakly depends on the nominal one, we obtain a bound that does not… (More)

For the prediction with expert advice setting, we consider methods to construct algorithms that have low adaptive regret. The adaptive regret of an algorithm on a time interval [t 1 , t 2 ] is the loss of the algorithm minus the loss of the best expert over that interval. Adaptive regret measures how well the algorithm approximates the best expert locally,… (More)

Classical probability theory considers probability distributions that assign probabilities to all events (at least in the finite case). However, there are natural situations where only part of the process is controlled by some probability distribution while for the other part we know only the set of possibilities without any probabilities assigned. We adapt… (More)

We introduce a new protocol for prediction with expert advice in which each expert evaluates the learner's and his own performance using a loss function that may change over time and may be different from the loss functions used by the other experts. The learner's goal is to perform better or not much worse than each expert, as evaluated by that expert, for… (More)

We study prediction with expert advice in the setting where the losses are accumulated with some discounting and the impact of old losses can gradually vanish. We generalize the Aggregating Algorithm and the Ag-gregating Algorithm for Regression, propose a new variant of exponentially weighted average algorithm, and prove bounds on the cumulative discounted… (More)

We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true distribution µ by the algorithmic complexity of µ. Here we assume we are at a time t > 1 and already observed x = x 1 ...x t. We bound the future prediction performance on x t+1 x… (More)

Real-world applications typically permit only constant time intervals between subsequent moves of an agent interacting with an environment. Hence there is a need to efficiently distribute the limited computation time and also other resources available for planning ahead and for evaluating alternative future action sequences. In this paper we study a… (More)

We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true distribution µ by the algorithmic complexity of µ. Here we assume that we are at a time t > 1 and have already observed x = x 1 ...x t. We bound the future prediction performance on… (More)