[Ml-stat-talks] Princeton Optimization Seminar: Kush Varshney, Thu Jan 22, 4:30PM

Amir Ali Ahmadi a_a_a at princeton.edu
Thu Jan 15 21:58:56 EST 2015


-----   Princeton Optimization Seminar   -----


DATE:  Thursday, January 22, 2014

TIME:  4:30pm

LOCATION:  Sherrerd Hall room 101

SPEAKER:  Kush Varshney, IBM Research

TITLE:  Learning Classification Rules via Boolean Compressed Sensing with Applications to Workforce Analytics

ABSTRACT:
Motivated by business analytics applications such as identifying employees at risk of voluntary attrition, we propose an interpretable rule-based classification system based on ideas from Boolean compressed sensing. We represent the problem of learning individual conjunctive clauses or individual disjunctive clauses as a Boolean group testing problem, and apply a novel linear programming relaxation to find solutions. We derive results for exact rule recovery which parallel the conditions for exact recovery of sparse signals in the compressed sensing literature. This is an exciting development in rule learning where most prior work focused on heuristic solutions. Furthermore we develop screening methods that use duality theory to dramatically reduce the size of the optimization problem through easily computable certificates that many of the variables must be zero in the optimal solution. We show competitive classification accuracy using the proposed approach.

BIO:
http://researcher.watson.ibm.com/researcher/view.php?person=us-krvarshn

===   Princeton Optimization Seminar   ===
If you would like to subscribe to the mailing list of the optimization seminar series, please visit the link below or send an email with
SUBSCRIBE opt-seminar in the body to listserv at lists.princeton.edu<mailto:listserv at lists.princeton.edu>.

https://lists.princeton.edu/cgi-bin/wa?SUBED1=opt-seminar&A=1
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20150116/e2757151/attachment.html>


More information about the Ml-stat-talks mailing list