[Ml-stat-talks] Wilks Statistics Seminar: Mehryar Mohri

Barbara Engelhardt bee at princeton.edu
Mon Sep 28 13:08:59 EDT 2015


***   Wilks Statistics Seminar   ***

DATE:  Friday, October 2, 2015

TIME:   12:30pm

LOCATION:   Sherrerd Hall, room 101

SPEAKER:    Mehryar Mohri, Computer Science Dept., NYU

TITLE:  Deep Boosting

ABSTRACT: This talk discusses a new ensemble learning algorithm, DeepBoost,
which can use as a base classifier set deep decision trees, or other rich
families. Extensive experiments show that DeepBoost consistently
outperforms AdaBoost, Logistic Regression, and their L1-regularized
variants. The key to the success of the algorithm is a capacity-conscious
selection criterion for the hypotheses forming the ensemble, which is
grounded in a new theoretical foundation with several significant
implications. The theory developed is quite general and leads a new model
selection framework, Voted Risk Minimization, which can guide the design of
a variety of other learning algorithms such as Structural Maxent or Deep
Cascade models.
Joint work with Corinna Cortes (Google Research), Vitaly Kuznetsov (Courant
Institute), and Umar Syed (Google Research).
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20150928/72658672/attachment.html>


More information about the Ml-stat-talks mailing list