American Statistical Association
New York City
Metropolitan Area Chapter

Levin Lecture Series: Fall 2018 Colloquium Seminars
Department of Biostatistics
Mailman School of Public Health
Columbia University



SCALABLE AND MODEL-FREE METHODS FOR MULTICLASS PROBABILITY ESTIMATION

by

Helen Zhang
Professor
Department of Mathematics
University of Arizona

Host: Dr. Seonjoo Lee


Abstract

Classical approaches for multiclass probability estimation are mostly model-based, such as logistic regression or LDA, by making certain assumptions on the underlying data distribution. We propose a new class of model-free methods to estimate class probabilities based on large-margin classifiers. The method is scalable for high-dimensional data by employing the divide-and-conquer technique, which solves multiple weighted large-margin classifiers and then constructs probability estimates by aggregating multiple classification rules. Without relying on any parametric assumption, the estimates are shown to be consistent asymptotically. Both simulated and real data examples are presented to illustrate performance of the new procedure.

This is joint work with Xin Wang and Yichao Wu.


Date: Thursday, October 18, 2018
Time: 11:45 A.M. - 12:45 P.M.
Location: Mailman School of Public Health
Department of Biostatistics
722 West 168th Street
AR Building
8th Floor Auditorium
New York, New York

The World of Statistics
Home Page | Chapter News | Chapter Officers | Chapter Events
Other Metro Area Events | ASA National Home Page | Links To Other Websites
NYC ASA Chapter Constitution | NYC ASA Chapter By-Laws

Page last modified on October 12, 2018
Copyright © 1998-2018 by New York City Metropolitan Area Chapter of the ASA
Designed and maintained by Cynthia Scherer
Send questions or comments to nycasa@nycasa.org