SoloGen

Large deviations for the local fluctuations of random walks and new insights into the “randomness” of Pi http://arxiv.org/abs/1004.3713v2

Active Learning Halfspaces under Margin Assumptions http://arxiv.org/abs/1112.1556v1

Predictors for time series with energy decay on higher frequencies http://arxiv.org/abs/1112.1478v1

Information-Theoretically Optimal Compressed Sensing via Spatial Coupling and Approximate Message Passing http://arxiv.org/abs/1112.0708v1

On the question of effective sample size in network modeling http://arxiv.org/abs/1112.0840v1

Multi-stage Convex Relaxation for Feature Selection http://arxiv.org/abs/1106.0565v2

Dimension adaptability of Gaussian process models with variable selection and projection

http://arxiv.org/abs/1112.0716v1

Machine learning with operational costs

http://arxiv.org/abs/1112.0698v1

Model Selection in Reinforcement Learning

Csaba Szepesvári and I have a new paper about the model selection problem in reinforcement learning. This paper, which is published by the Machine Learning Journal, considers the batch (offline, non-interactive) reinforcement learning setting when the goal is to find an action-value function with the smallest Bellman error among a countable set of candidate functions. We prove an oracle-like inequality and show that under some additional conditions this leads to an adaptive algorithm.

For more information the results, take a look at the paper here (or here for the version on the MLJ journal website — subscription required).