Venue: Venue TBA
The Ph.D. in Scientific Computing program is intended for students who will make extensive use of large-scale computation, computational methods, or algorithms for advanced computer architectures in their doctoral studies. This seminar series showcases the breadth of research covered by the program.
He is from industrial and Operations Engineering department and is working on constrained stochastic optimization.
We propose a stochastic method for solving equality constrained optimization problems that utilizes predictive variance reduction. Specifically, we develop a method based on the sequential quadratic programming paradigm that employs variance reduction in the gradient approximations. Under reasonable assumptions, we prove that a measure of first-order stationarity evaluated at the iterates generated by our proposed algorithm converges to zero in expectation from arbitrary starting points, for both constant and adaptive step size strategies. Finally, we demonstrate the practical performance of our proposed algorithm on constrained binary classification problems that arise in machine learning.
This event is part of MICDE’s seminar series featuring Ph.D. students in the Scientific Computing program. This series is open to all. University of Michigan faculty and students interested in computational and data sciences are encouraged to attend.
Questions? Email MICDEemail@example.com