Plenary Talk

The 55th Annual Allerton Conference on Communications, Control, and Computing Plenary Lecture will be given on Friday, October 6, 2017, at 8:30-9:30 a.m. by Professor John Lafferty from the Department of Statistics and Data Science at Yale University.

Title:  Structure and Adaptivity in Optimization, Learning and Inference

Abstract:   

Problem structure typically must be exploited for optimal optimization and learning algorithms. Adaptive procedures over large classes of models are a kind of hedge against making weak assumptions. In this talk we discuss recent work related to this general theme. First, we present a notion of fine scale adaptivity in convex optimization, bridging concepts between statistics and numerical analysis. Next, we discuss adaptivity and structure for shape constrained problems that generalize isotonic regression. Finally, we describe some recent work on testing for structure in random networks, where visualization played an important role in uncovering effective testing procedures.

Biography:  

John Lafferty is Professor in the Department of Statistics and Data Science at Yale University, with a secondary appointment in Computer Science. Before joining Yale, Lafferty was Louis Block Professor in the Department of Statistics and the Department of Computer Science at the University of Chicago, and also Adjunct Professor at the Toyota Technological Institute of Chicago. Professor Lafferty’s research area is statistical machine learning, with a focus on nonparametric methods and theory, computation, high-dimensional data, graphical models, and text modeling.

Lafferty received his doctoral degree in mathematics from Princeton University, where he was a member of the Program in Applied and Computational Mathematics. Prior to joining the University of Chicago in 2011, he was a faculty member in the Computer Science Department at Carnegie Mellon University, where he was also in the Machine Learning Department and the Department of Statistics. He got his start in the general area of machine learning while working on problems in language processing and statistical machine translation at the IBM Watson Research Center in Yorktown Heights, NY.

Save

Save