IOE 899 Seminar: Jorge Nocedal
Jorge Nocedal, Northwestern University, "Optimization Methods for Deep Neural Networks"
Abstract: We discuss the main challenges facing optimization methods for very large scale machine learning problems. Two case studies illustrate how convex and nonconvex models arise in practice, and we describe the most popular optimization techniques employed at present. The second part of the talk will be devoted to some surprising observations about the optimization of deep neural networks.
Bio: Jorge Nocedal is the David and Karen Sachs Professor of Industrial Engineering and Management Sciences at Northwestern University. His research is in nonlinear optimization, deterministic and stochastic, with applications in machine learning. Over the years, his work has spanned algorithms, analysis and software. He is a SIAM Fellow, has been an invited speaker at the International Congress of Mathematicians, and was awarded the 2012 George B. Dantzig Prize.