Matthew W. Hoffman

I am currently a graduate student in the CS department at UBC, supervised by Nando de Freitas and Arnaud Doucet. I'm working on various approaches to reformulate stochastic control problems as inference problems, particularly in large, continuous domains.

I was previously an undergraduate in the CS and Math departments at the University of Washington. While there I worked with Rajesh Rao as part of the Neural Systems Group. I focused primarily on problems of gaze-imitation and imitation-learning utilizing shared-attention. For further information see the relevant publications.

Finally, you can also take a look at my CV.

Updates

I recently created a calendar for talks at UBC that are of interest to machine learning students. There is also an ical file available. If you'd like access to edit/add events/etc. just send me an email.

There is also a reading group on bandits this term that I am nominally "leading" (which really just means that I made the webpage).

I'll be at EWRL in early September presenting some work we've done on feature selection in RL. Come talk to me there!

Publications

M. Hoffman, E. Brochu, N. de Freitas. Portfolio Allocation for Bayesian Optimization. UAI, 2011.
M. Ghavamzadeh, A. Lazaric, R. Munos, M. Hoffman. Finite sample analysis of Lasso-TD. ICML, 2011.
M. Hoffman and N. de Freitas. Inference strategies for solving semi-Markov decision processes. To appear in Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions, L.E. Sucar, E. Morales, H. Hoey (Eds.), 2010.
M. Hoffman, P. Carbonetto, N. de Freitas, and A. Doucet. Inference strategies for solving semi-Markov decision processes. NIPS Workshop on Probabilistic Approaches for Robotics and Control, 2009.
M. Hoffman, H. Kueck, N. de Freitas, A. Doucet. New inference strategies for solving Markov Decision Processes using reversible jump MCMC. UAI, 2009.
H. Kueck, M. Hoffman, A. Doucet, N. de Freitas. Inference and Learning for Active Sensing, Experimental Design, and Control. Invited paper, IBPRIA, 2009.
M. Hoffman, N. de Freitas, A. Doucet, Jan Peters. An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Rewards. AISTATS, 2009. (errata).
M. Hoffman, A. Doucet, N. de Freitas, and A. Jasra. Bayesian policy learning with trans-dimensional MCMC. NIPS, 2007. (This is an extended and greatly revised version of UBC CS TR-2007-04.)
M. Hoffman, A. Doucet, N. de Freitas, and A. Jasra. On Solving General State-Space Sequential Decision Problems using Inference Algorithms. UBC CS TR-2007-04. March, 2007.
M. Hoffman, D. Grimes, A. Shon, and R. Rao. A probabilistic model of gaze imitation and shared attention. Neural Networks 19(3): Special Issue on Brain Mechanisms of Imitation; 2006.
A. Shon, D. Grimes, C. Baker, M. Hoffman, S. Zhou, R. Rao. Probabilistic gaze imitation and saliency learning in a robotic head. ICRA, 2005.

Notes

The following are collections of notes mostly made so that I can remember how to solve some particular problem: