Events

MIT Distinguished Seminar Series in Computational Science and Engineering
Thursday, February 8, 2018 | 12:00 PM | 56-114

Optimization Methods for Training Neural Networks
Jorge Nocedal
Walter P. Murphy Professor, Department of Industrial Engineering and Management Sciences
Northwestern University

Most high-dimensional nonconvex optimization problems cannot be solved to optimality. It has been observed, however, that deep neural networks have a benign geometry that permits standard optimization methods to find acceptable solutions. However, solution times can be exorbitant. In addition, not all minimizers of the neural network loss functions are equally desirable, as some lead to prediction systems with better generalization properties than others. In this talk we discuss classical and new optimization methods in the light of these observations, and conclude with some open questions.

MIT Distinguished Seminar Series in Computational Science and Engineering
Thursday, April 26, 2018 | 12:00 PM | 56-114

Mauro Maggioni
Bloomberg Distinguished Professor of Mathematics and Applied Mathematics
Johns Hopkins University

MIT Distinguished Seminar Series in Computational Science and Engineering
Thursday, May 10, 2018 | 12:00 PM | 56-114

Philipp Hennig
Max Planck Research Group Leader, Probabilistic Numerics
Max Planck Institute for Intelligent Systems, Tübingen, Germany