Theory Lunch Seminar

  • Remote Access Enabled - Zoom
  • Virtual Presentation
  • ILIAS DIAKONIKOLAS
  • Professor
  • Department of Computer Sciences
  • University of Wisconsin-Madison
Seminars

Learning with Massart Noise

 I will start with a brief overview of high-dimensional supervised learning (PAC learning) in the presence of noise.  The main part of the talk will focus on a recent work (with Gouleakis and Tzamos) which gave the first distribution-independent learning algorithm for halfspaces in the Massart noise model. 

Zoom Participation. See announcement.

CMU Theory Youtube channel.

For More Information, Please Contact: 
Keywords: