I’m a postdoc fellow at Vector Institute, where I’m hosted by Chris J. Maddison. I received my PhD degree in computer science at Purdue University, where I was advised by Bruno Ribeiro. Before that —in a distant and happy land— I was a BSc student (also in CS) at UFMG, Brazil. During my time as an undergrad I worked with distributed algorithms (at UFMG) and quantum computing theory (at University of Calgary).
I’m broadly interested in statistical and causal machine learning. More specifically, I study the interplay between symmetries, computation, and learning. How can we leverage these concepts to build better (and practical) machine learning methodology? I believe these insights are specially relevant in problems with complex systems’ data. Inspired by this, more recently I have been considering problems with applications in biochemistry.
New pre-print available! “Probabilistic Invariant Learning with Randomized Linear Classifiers” is now on arXiv.
Our work on “Causal Lifting and Link Prediction” is now published (w/ open access) in the Proceedings of the Royal Society A. Click here to check it out.
I started as a Postdoc Fellow at the Vector Institute! If you’re ever in Toronto and want to talk research, drop me a line!