Matthew W. Hoffman

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.

Recent News

Recent publications and preprints

  1. 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]

  2. Hoffman, M. W., & Ghahramani, Z. (2015). Output-Space Predictive Entropy Search for Flexible Global Optimization. In the NIPS workshop on Bayesian optimization. [pdf] [bibtex]

  3. 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]