Bernardo Ávila Pires (@ University of Alberta)


I am a PhD (Statistical Machine Learning) candidate at the Department of Computing Science of the University of Alberta, and my supervisor is Csaba Szepesvári.

Contact information

1-01 Athabasca Hall,
University of Alberta
Edmonton, AB
T6G 2E8
At the University of Alberta ( I am bpires.


Currently, I am working in two areas: multiclass classification and model-based reinforcement learning, but my research interests include supervised learning, online learning and reinforcement learning. I have been approaching machine learning research in a theoretical way, and I am eager to explore problems where practical challenges and empirical observations guide the development of theory, and theory guides the design of better algorithms.

Multiclass classification. My interests in this problem stem out from calibration and how to design/evaluate convex losses for multiclass classification, but touch on other issues such as sample complexity. I am also curious to see how developments in calibration and sample complexity work in structured prediction problems.

Model-based reinforcement learning. We wish to design/describe methods for planning in MDPs. What should the model of an MDP be like? What are the properties of a good model? How flexible can we make our models, without losing these properties?


I have been a teaching assistant for many (non-consecutive) terms at the University of Alberta. I have had the opportunity to work with great professors, instructors, fellow TAs and students. The experience I enjoyed the most were the lab times, where I got to challenge students to succeed on problems, and where they challenged me to explain concepts clearly, concisely and intuitively. I have even honored with a Teaching Assistant Award by the Faculty of Science, in 2014.


My CV has more information on my degrees, publications, awards and activities.

Other pages

Google Scholar