In 2005, the Applied Probability Society initiated the annual Markov Lecture, to be delivered in the fall of each year at the INFORMS Annual Meeting. The intent is to both honor the associated speaker and to bring to the APS membership topical work of the highest calibre in our discipline. The Markov Lecturer is selected by the APS prize committee.
2024 Markov Lecturer
Devavrat Shah
Electrical Engineering and Computer Science
Massachusetts Institute of Technology
Operations Research and Information Engineering (ORIE)
Cornell University
Title: Various Incarnations of Matrix Completion
Abstract: The objective of matrix completion is to estimate or complete an unknown matrix from its partial, noisy observations. Since its introduction as a model for recommendation systems in the 1990s, it has been central to advances in machine learning, statistics, and applied probability. In this talk, I will discuss a few incarnations of it that arise in the context of time-series analysis, causal inference, reinforcement learning and empirical risk minimization.
* If you gave the lecture or led the discussion in the past and want to share your slides, please contact the APS Webmaster.