398 citations
- Dalle Molle Institute for Artificial Intelligence ResearchCH3 papers
- The University of MelbourneAU3 papers
- Chinese University of Hong KongHK2 papers
- UNSW SydneyAU2 papers
- Australian National UniversityAU1 paper
- Centrum Wiskunde & InformaticaNL1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- Graz University of TechnologyAT1 paper
- Leiden UniversityNL1 paper
- Ludwig-Maximilians-Universität MünchenDE1 paper
- Max Planck Institute for Biological CyberneticsDE1 paper
- Stanford UniversityUS1 paper
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2008★ 16 cited
Temporal Difference Updating without a Learning Rate
Marcus Hutter, Shane Legg
We derive an equation for temporal difference learning from statistical principles. Specifically, we start with the variational principle and then bootstrap to produce an updating…
cs.LG2008★ 250 cited
A Kernel Method for the Two-Sample Problem
Arthur Gretton, Karsten Borgwardt, Malte J. Rasch +2
We propose a framework for analyzing and comparing distributions, allowing us to design statistical tests to determine if two samples are drawn from different distributions. Our te…
cs.LG2007★ 10 cited
Algorithmic Complexity Bounds on Future Prediction Errors
A. Chernov, M. Hutter, J. Schmidhuber
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor from the true d…