Our research Here are the main topics on which our group works. Adversarial machine learningAdversarial learning corresponds to trying to build models which are robust to malicious adversaries. Theory of deep learningUnderstanding the performance of neural networks is certainly one of the most thrilling challenges for the current machine learning community. Stochastic optimisationThe tremendous success of machine learning in recent years is largely due to the impressive performances of stochastic optimisation algorithms such as SGD. MCMC algorithmsMarkov chain Monte Carlo (MCMC) algorithms are a powerful, computational tool for Bayesian inference.