398 citations · 1.8k across the 163 of their papers we have counts for
7 papers · 1 filter
Fast Non-Parametric Bayesian Inference on Infinite Trees
Marcus Hutter
Given i.i.d. data from an unknown distribution, we consider the problem of predicting future items. An adaptive way to estimate the probability density is to recursively subdivide…
Universal Convergence of Semimeasures on Individual Random Sequences
Marcus Hutter, Andrej Muchnik
Solomonoff's central result on induction is that the posterior of a universal semimeasure M converges rapidly and with probability 1 to the true sequence generating posterior mu, i…
On the Convergence Speed of MDL Predictions for Bernoulli Sequences
Jan Poland, Marcus Hutter
We consider the Minimum Description Length principle for online sequence prediction. If the underlying model class is discrete, then the total expected square loss is a particularl…
Prediction with Expert Advice by Following the Perturbed Leader for General Weights
Marcus Hutter, Jan Poland
When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the a…
Convergence of Discrete MDL for Sequential Prediction
Jan Poland, Marcus Hutter
We study the properties of the Minimum Description Length principle for sequence prediction, considering a two-part MDL estimator which is chosen from a countable class of models.…
Tournament versus Fitness Uniform Selection
Shane Legg, Marcus Hutter, Akshat Kumar
In evolutionary algorithms a critical parameter that must be tuned is that of selection pressure. If it is set too low then the rate of convergence towards the optimum is likely to…