I’m a first year PhD student in the machine learning department at Carnegie Mellon University.
Previously, I was the lead research analyst at Stanford’s RegLab. Prior to Stanford I was a master’s student at Oxford’s Mathematical Institute, and before that I was an undergraduate in maths and computer science at UBC. Sometime before that I played Lego and watched a lot of Blue’s Clues.
You can contact me at benchugg \(\alpha\tau\) cmu.edu. In accordance with the bizarre norms of academia, here is my CV.
My primary interests at the moment involve developing robust algorithms for sequential problems, particularly in nonparametric settings. I’m increasingly interested in game-theoretic statistics, and algorithmic statistics more generally, for this purpose. Previously, I worked on problems in graph theory, combinatorial optimization, and stochastic reaction networks.
Ideally, I try and straddle the borderlands between theory and practice with a bias towards the former, but apparently the results have high variance because I’ve spent time doing doing both pure theory and pure application.
The podcast is mostly an attempt to break out of the academic echo chamber and talk about things other than limit theorems and algorithmic performance. We have a few beers and chat about anything from moral philosophy and thought experiments, to the philosophy of logic, climate change, free will, dualism, and social media.
We also have an ongoing series on Conjectures and Refutations by Karl Popper.