Marc Deisenroth

Lecturer in Statistical Machine Learning

Department of Computing, Imperial College London

Bio

Marc Deisenroth is a Lecturer (equivalent to an Assistant Professor in the US) in Statistical Machine Learning at the Department of Computing, Imperial College London. Since September 2016, Marc has been an advisor to PROWLER.io, a Cambridge-based startup. Prior to his appointment, he was an Imperial College Research Fellow (09/2013–06/2015), Group Leader at TU Darmstadt (12/2011–08/2013), and Research Associate at the University of Washington and Intel Labs Seattle (02/2010–12/2011). Marc was awarded a PhD in Machine Learning in 2009. His supervisor was Carl Edward Rasmussen.

Marc was Program Chair of EWRL 2012, Workshops Chair of RSS 2013 and received Best Paper Awards at ICRA 2014 and ICCAS 2016. He is a recipient of a Google Faculty Research Award and a Microsoft PhD Scholarship. Marc's research interests center around data-efficient and autonomous machine learning.

Research Expertise

  • Machine Learning: Data-efficient machine learning, Gaussian processes, reinforcement learning, Bayesian optimization, approximate inference, deep probabilistic models
  • Robotics/Control: Robot learning, legged locomotion, planning under uncertainty, imitation learning, adaptive control, robust control, learning control, optimal control
  • Signal Processing: Nonlinear state estimation, Kalman filtering, time-series modeling, dynamical systems, system identification, stochastic information processing

Key Publications

  1. Gaussian Processes for Data-Efficient Learning in Robotics and Control, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
  2. Robust Filtering and Smoothing with Gaussian Processes, IEEE Transactions on Automatic Control, 2012
  3. Distributed Gaussian Processes, ICML, 2015
  4. Expectation Propagation in Gaussian Process Dynamical Systems, NIPS, 2012
  5. Gaussian Process Dynamic Programming, Neurocomputing, 2009
  6. A Survey on Policy Search for Robotics, NOW Publishers, 2013
  7. Probabilistic Movement Modeling for Intention-based Decision Making, International Journal of Robotics Research, 2013