I’m currently a research scientist at Google DeepMind and until recently I was a postdoctoral researcher in the machine learning group at the University of Cambridge. I work on probabilistic approaches to sequential decision making and optimization.
August 12, 2016. Our paper on Learning to learn by gradient descent by gradient descent was accepted at NIPS 2016. See you in Barcelona!
January 1, 2016. I have accepted a position as a research scientist at Google DeepMind and am excited to join this coming March!
December 12, 2015. I spoke at the NIPS workshop on Bayesian optimization and presented recent work on output-space PES.
Andrychowicz, M., Denil, M., Gomez, S., Hoffman, M. W., Pfau, D., Schaul, T., & de Freitas, N. (2016). Learning to learn by gradient descent by gradient descent. In Neural Information Processing Systems. [pdf] [bibtex]
Hoffman, M. W., & Ghahramani, Z. (2015). Output-Space Predictive Entropy Search for Flexible Global Optimization. In the NIPS workshop on Bayesian optimization. [pdf] [bibtex]
Hernández-Lobato, J. M., Gelbart, M. A., Hoffman, M. W., Adams, R. P., & Ghahramani, Z. (2015). Predictive Entropy Search for Bayesian Optimization with Unknown Constraints. In the International Conference on Machine Learning. [pdf] [bibtex]