Events Calendar

Statistics Department Research Seminar

Speaker: Bryon Aragam

     Carnegie Mellon University


Topic: Identifiability of nonparametric mixture models, clustering, and semi-supervised learning


Place: Kelly Engineering Center 1003

                        This seminar is open to the public


Motivated by problems in data clustering and semi-supervised learning, we establish general conditions under which families of nonparametric mixture models are identifiable by introducing a novel framework for clustering over fitted parametric (i.e. misspecified) mixture models. These conditions generalize existing conditions in the literature, allowing for general nonparametric mixture components. After a discussion of some statistical aspects of this problem (e.g. estimation), we will discuss two applications of this framework. First, we extend classical model-based clustering to nonparametric settings and develop a practical algorithm for learning nonparametric mixtures. Second, we analyze the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional distributions. Under these assumptions, we establish an \Omega(K\log K) labeled sample complexity bound without imposing parametric assumptions, where K is the number of classes. These results suggest that even in nonparametric settings it is possible to learn a near-optimal classifier using only a few labeled samples. 

Monday, October 8, 2018 at 4:00pm to 5:00pm

Kelley Engineering Center, Room 1003
110 SW Park Terrace, Corvallis, OR 97331

Event Type

Lecture or Presentation

Event Topic



Faculty and Staff, Student, Alumni




Open to public - Free

Department of Statistics


Contact Name

Katie McLaughlin

Contact Email

Contact Phone


Google Calendar iCal Outlook

Recent Activity