Name: Information-theoretic lower bounds for distributed statistical estimation with communication constraints
Start: 2013-12-07T15:10:00-0800
End: 2013-12-07T15:30:00-0800

Back To Schedule

Information-theoretic lower bounds for distributed statistical estimation with communication constraints

We establish minimax risk lower bounds for distributed statistical estimation given a budget $B$ of the total number of bits that may be communicated. Such lower bounds in turn reveal the minimum amount of communication required by any procedure to achieve the classical optimal rate for statistical estimation. We study two classes of protocols in which machines send messages either independently or interactively. The lower bounds are established for a variety of problems, from estimating the mean of a population to estimating parameters in linear regression or binary classification.
None

Speakers

John Duchi

Michael Jordan

Michael I. Jordan is the Pehong Chen Distinguished Professor in the Department of Electrical Engineering and Computer Science and the Department of Statistics at the University of California, Berkeley. His research in recent years has focused on Bayesian nonparametric analysis, probabilistic... Read More →