The University of Arizona
Please note that this event has ended!

Sparsity and Structure in Large Scale Learning and Optimization

Special Colloquium

Sparsity and Structure in Large Scale Learning and Optimization
Series: Special Colloquium
Location: MATH 501
Presenter: Yury Maximov, Los Alamos National Laboratory, Theoretical Division T-5 and CNLS

 In this talk, I introduce our recent results on the complexity of convex optimization methods for solving high-dimensional machine learning and statistical estimation problems. The primary focus of this research is hidden problem sparsity and structure that numerical algorithms could utilize to accelerate numerical algorithms of large-scale problems such as LASSO and PageRank. Further, we investigate the sparsity of classification problems and its influence on the complexity and reliability of binary and multi-class classification methods. Finally, I present some motivating engineering applications along with the results of numerical experiments justifying the efficiency of the proposed algorithms and compare them with state-of-the-art algorithms and commercial solvers.

(Refreshments will be served in the Math Commons Room at 3:30 PM)