Title:

Optimization in Learning and Data Analysis

Abstract:
Optimization tools are vital to data analysis and learning. The optimization perspective has provided valuable insights, and optimization formulations have led to practical algorithms with good theoretical properties. In turn, the rich collection of problems in
learning and data analysis is providing fresh perspectives on optimization algorithms and is driving new fundamental research in the area. After a brief survey, we focus on several problems --- signal reconstruction, manifold learning, and regression/classification ---
describing in each case recent research in which optimization algorithms have been developed and applied successfully.

Bio:

• Professor in the Computer Sciences Department and Industrial and Systems Engineering at UW-Madison
• Investigator in the Optimization Theme in the Wisconsin Institute for Discovery at UW-Madison.
• Past Chair and current Vice Chair of the Mathematical Optimization Society (formerly Mathematical Programming Society).
• SIAM Fellow and Member of the Board of Trustees of SIAM.
• Member of the Science Advisory Board of IPAM.

http://www.cs.wisc.edu/users/swright