Ohio State nav bar

Seminar: Vince Vu

Vince Vu
February 1, 2018
All Day
209 W. Eighteenth Ave. (EA), Room 170

Title

Group invariance and computational sufficiency

Speaker

Vince Vu, Department of Statistics, The Ohio State University

Abstract

Statistical sufficiency formalizes the notion of data reduction. In the decision theoretic interpretation, once a model is chosen all inferences should be based on a sufficient statistic.  However, suppose we start with a set of methods that share a sufficient statistic rather than a specific model.  Is it possible to reduce the data beyond the statistic and yet still be able to compute all of the methods?  In this talk, I'll present some progress towards a theory of "computational sufficiency" and show that strong reductions _can_ be made for large classes of penalized M-estimators by exploiting hidden symmetries in the underlying optimization problems.  These reductions can (1) enable efficient computation and (2) reveal hidden connections between seemingly disparate methods.  As a main example, I'll show how the theory provides a surprising answer to the following question: "What do the Graphical Lasso, sparse PCA, single-linkage clustering, and L1 penalized Ising model selection all have in common?"

Note: Seminars are free and open to the public. Reception to follow.