Goeffrey's paper, titled “Mixing Time Estimation in Ergodic Markov Chains from a Single Trajectory with Contraction Methods" is published in the proceedings of the 31st International Conference on Algorithmic Learning Theory (ALT 2020), held in San Diego, California (USA), on Feb. 2020. ALT 2020, is a top venue for machine learning theory, and is highly competitive.
Geoffrey's primary research interest is in the field of applied probability and mathematical statistics, supervised by Prof. Aryeh Kontorovich. In particular, he focuses on contributing to the development of the finite-sample theory of statistical problems, when the collected data is not independent and identically distributed, but rather assumed to be drawn from a Markovian process, i.e. when the (conditional) probability of an event occurring depends solely on the previous one.