Intro

I am a post-doctoral researcher at the Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh, currently working in the MilePost (Machine Learning for Embedded Programs Optimisation) project

I am leading the development and application of machine learning techniques to computer systems problems such as compiler optimization and micro-architectural adaptivity control. During my PhD studies I developed probabilistic machine learning methods for adaptive program optimization, as part of the COLO (COmpilers that Learn to Optimize) project.

I work closely with professor Chris Williams and professor Michael O'Boyle. In the past, I also collaborated with Felix Agakov and John Cavazos.

Research Interests

My research focuses on the development of probabilistic models for the construction of systems that can learn from their past experience and for the analysis of complex (and possibly very high dimensional) structured data. Therefore, my research lies at the intersection of machine learning, statistics, computer science and artificial intelligence.

In particular, I am interested in graphical models; Bayesian statistics; transfer learning; Gaussian processes; learning from structured data; reinforcement learning; optimization; and applications including adaptive optimizing compilation, micro-architectural design, computer vision and robotics.

Publications

(New!) Dubach, C.; Jones, T. M.; Bonilla, E. V.; Fursin, G.; and O'Boyle, M. F. Portable compiler optimization across embedded programs and microarchitectures using machine learning. In Proceedings of the 42nd IEEE/ACM International Symposium on Microarchitecture, 2009. To Appear.
[ bib ]

Fursin, G.; Chamski, Z.; Miranda, C.; Temam, O.; Namolaru, M.; Yom-Tov, E.; Zaks, A.; Mendelson, B.; Barnard, P.; Ashton, E.; Courtois, E.; Bodin, F.; Bonilla, E.; Thomson, J.; Leather, H.; Williams, C.; and O'Boyle, M. MilePost GCC: A machine learning enabled self-tuning compiler. International Journal of Parallel Programming, 2009. Under review.
[ bib ]

Leather, H.; Bonilla, E.; and O'Boyle, M. Automatic feature generation for machine learning based optimizing compilation. In Proceedings of the International Symposium on Code Generation and Optimization, pages 81-91. IEEE Computer Society, Washington, DC, USA, 2009.
[ bib | .pdf ]

Fursin, G.; Miranda, C.; Temam, O.; Namolaru, M.; Yom-Tov, E.; Zaks, A.; Mendelson, B.; Barnard, P.; Ashton, E.; Courtois, E.; Bodin, F.; Bonilla, E.; Thomson, J.; Leather, H.; Williams, C.; and O'Boyle, M. MILEPOST GCC: machine learning based research compiler. In Proceedings of the GCC Developers' Summit. Ottawa, Canada, 2008.
[ bib | .pdf ]

Bonilla, E. V. Compilers that Learn to Optimise: A Probabilistic Machine Learning Approach. Ph.D. thesis, School of Informatics, The University of Edinburgh, 2008.
[ bib ]

Bonilla, E. V.; Chai, K. M. A.; and Williams, C. K. I. Multi-task Gaussian process prediction. In J. Platt; D. Koller; Y. Singer; and S. Roweis, editors, Advances in Neural Information Processing Systems 20. MIT Press, Cambridge, MA, 2008.
[ bib | .pdf | note ]

Williams, C. K. I.; Chai, K. M. A.; and Bonilla, E. V. A note on noise-free Gaussian process prediction with separable covariance functions and grid designs. Technical Report EDI-INF-RR-1228, University of Edinburgh, 2007.
[ bib | .pdf ]

Bonilla, E. V.; Agakov, F. V.; and Williams, C. K. I. Kernel multi-task learning using task-specific features. In Proceedings of the 11th International Conference on Artificial Intelligence and Statistics. Omnipress, 2007.
[ bib | .pdf ]

Cavazos, J.; Fursin, G.; Agakov, F.; Bonilla, E.; O'Boyle, M. F. P.; and Temam, O. Rapidly selecting good compiler optimizations using performance counters. In Proceedings of the International Symposium on Code Generation and Optimization, pages 185-197. IEEE Computer Society, Washington, DC, USA, 2007.
[ bib | .pdf ]

Bonilla, E. V.; Williams, C. K. I.; Agakov, F. V.; Cavazos, J.; Thomson, J.; and O'Boyle, M. F. P. Predictive search distributions. In W. W. Cohen and A. Moore, editors, Proceedings of the 23rd international conference on Machine learning, pages 121-128. ACM, New York, NY, USA, 2006.
[ bib | .pdf ]

Cavazos, J.; Dubach, C.; Agakov, F.; Bonilla, E.; O'Boyle, M. F. P.; Fursin, G.; and Temam, O. Automatic performance model construction for the fast software exploration of new hardware designs. In Proceedings of the international conference on Compilers, architecture and synthesis for embedded systems, pages 24-34. ACM, New York, NY, USA, 2006.
[ bib | .pdf ]

Agakov, F.; Bonilla, E.; Cavazos, J.; Franke, B.; Fursin, G.; O'Boyle, M.; Thomson, J.; Toussaint, M.; and Williams, C. Using machine learning to focus iterative optimization. In Proceedings of the International Symposium on Code Generation and Optimization, pages 295-305. IEEE Computer Society, Washington, DC, USA, 2006.
[ bib | .pdf ]

Bonilla, E. V. Predicting the effect of loop unrolling using machine learning. In Proceedings of the Postgraduate Research Conference in Electronics, Photonics, Communications and Software. Lancaster, UK, 2005.
[ bib ]

Bonilla, E. V. Predicting Good Compiler Transformations Using Machine Learning. Master's thesis, School of Informatics, University of Edinburgh, UK, 2004.
[ bib ]

Older (In Spanish)

Salazar, A.; Bonilla, E.; Conzález, G.; and Rodríguez, M. A. Modificaciones de la señal de voz en tiempo y frecuencia. Mundo Eléctrico Colombiano, 16(46):108-110, 2002.
[ bib ]

Bonilla, E.; Salazar, A.; Conzález, G.; and Rodríguez, M. A. Codificación de la voz basada en un modelo sinusoidal. Mundo Eléctrico Colombiano, 16(45):48-50, 2001.
[ bib ]