MIT-MSR ML seminar: John Lafferty: Statistical Estimation Under Communication Constraints
Date: Wednesday, March 02, 2016
Time: 3:00 PM to 4:00 PM
Location: Seminar Room D463 (Star)
Host: Stefanie Jegelka, Adam Kalai
Contact: Stefanie S. Jegelka, email@example.com
Speaker URL: None
TALK: MIT-MSR ML seminar: John Lafferty: Statistical Estimation Under Communication Constraints
Statistical Estimation Under Communication Constraints
Imagine that I estimate a statistical model from data, and then want to share my model with you. But we are communicating over a resource constrained channel. By sending lots of bits, I can communicate my model accurately, with little loss in statistical risk. Sending a small number of bits will incur some excess risk. What can we say about the tradeoff between statistical risk and the communication constraints? This is a type of rate distortion and constrained minimax problem, for which we provide a sharp analysis in certain nonparametric settings. Joint work with Yuancheng Zhu (University of Chicago).
Created by Stefanie S. Jegelka at Saturday, February 06, 2016 at 10:13 AM.