ARC Colloquium: Sivan Sabato, Microsoft Research New England

Event Details
  • Date/Time:
    • Monday November 25, 2013 - Tuesday November 26, 2013
      12:00 pm - 11:59 am
  • Location: Klaus 1116W
  • Phone:
  • URL:
  • Email:
  • Fee(s):
  • Extras:


Summary Sentence: No summary sentence submitted.

Full Summary: No summary paragraph submitted.

Speaker: Sivan Sabato

Title: Auditing: Active Learning with Outcome-Dependent Query Costs

Abstract: We propose a learning setting in which unlabeled data is free, and the cost of a label depends on its value, which is not known in advance. Specifically, we study binary classification in an extreme case, where the algorithm only pays for negative labels. Our motivation is applications such as fraud detection, in which investigating an honest transaction should be avoided if possible. We term the setting "auditing", and consider the "auditing complexity" of an algorithm. We design auditing algorithms for simple hypothesis classes,
and show that with these algorithms, the auditing complexity can be significantly lower than the active label complexity. We also consider a general competitive approach for auditing,

and demonstrate its potential for linear classification.

Joint work with Anand Sarwate and Nati Srebro from TTI-Chicago

Additional Information

In Campus Calendar

College of Computing, School of Computer Science, ARC

Invited Audience
Undergraduate students, Faculty/Staff, Graduate students
No keywords were submitted.
  • Created By: Elizabeth Ndongi
  • Workflow Status: Published
  • Created On: Nov 14, 2013 - 12:00pm
  • Last Updated: Apr 13, 2017 - 5:23pm