Michael Jordan, University of California at Berkeley

Wed, Mar 4, 2015, 4:30 pm to 5:30 pm
Computer Science, Room 105
Further Explorations at the Computational and Statistical Interface

One of the grand challenges of our era is the attempt to bring computational and statistical ideas together in a theoretically- grounded framework for scalable statistical inference. This is made challenging by the lack of a role for computational concepts such as "runtime" in core statistical theory and the lack of a role for statistical concepts such as "risk" in core computational theory. I discuss our ongoing attempts to build bridges between "computational thinking" and "inferential thinking," including the theoretical study of lower bounds that embody computational and statistical constraints, and the development of procedures that make controlled use of parallel and distributed architectures in statistical inference.