[Ml-stat-talks] PACM Colloquium - April 25, 2011
amits at math.Princeton.EDU
Tue Apr 19 10:36:57 EDT 2011
DATE: Monday, April 25, 2011
PLACE: 214 Fine Hall
TIME: 4:00 pm
SPEAKER: Boaz Nadler, Weizmann Institute -- Israel
TITLE: Learning from Labeled and Unlabeled Data: Global vs. Multiple Approaches
In recent years there is increasing interest in learning from both labeled and unlabeled data (a.k.a. semi-supervised learning, or SSL). The key assumption in SSL, under which an abundance of unlabeled data may help, is that there is some relation between the unknown response function to be learned and the marginal density of the predictor variables. In the first part of this talk I'll present a statistical analysis of two popular graph based SSL algorithms: Laplacian regularization method and Laplacian eigenmaps. In the second part I'll present a novel multiscale approach for SSL as well as supporting theory. Some intimate connections to harmonic analysis on abstract data sets will be discussed. Joint work with Nati Srebro (TTI), Xueyuan Zhou (Chicago), Matan Gavish (WIS/Stanford) and Ronald Coifman (Yale).
Coffee & Tea will be served at 3:45 p.m. in 217A Fine Hall
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Ml-stat-talks