EECS 500 Seminar

Statistical and Adversarial Frameworks for Prediction Problems

Ambuj Tewari

Assistant Professor
University of Michigan, Department of Statistics & Department of EECS
Friday, November 01, 2013
12:30pm - 1:30pm
1311 EECS

Add to Google Calendar

About the Event

Machine learning theory has developed a variety of theoretical frameworks for the design and analysis of learning algorithms. This talk will introduce two well studied frameworks: statistical and adversarial. In the former, data is assumed to be generated using a probabilistic mechanism whereas in the adversarial framework, it could have been generated by a malicious adversary and is revealed to the learner sequentially. We will see how a fundamental measure of statistical complexity, called the Rademacher complexity, has a nice analog in the adversarial framework. The talk will end by providing pointers to global and local resources for students wishing to enter the fascinating area of research in machine learning theory.

Additional Information

Contact: Ann Pace

Phone: 763-5022


Sponsor(s): University of Michigan, Department of Electrical Engineering & Computer Science

Open to: Public