Separating Sources and Analysing Connectivity in EEG/MEG Using Probabilistic Models
Deep Reinforcement Learning
Some Recent Bandit Results
Markov Chain Monte Carlo Methods
Empirical Portfolio Selection
On the Complexity of A/B Testing
On the Quantitative Analysis of Deep Belief Networks
Bounding the Gaussian Process Information Gain: Applications to PAC-Bayes and GP Bandit Optimization
Confidence in nonparametric credible sets?
Bandit Algorithms for Online Linear Optimization