Academy of Mathematics and Systems Science, CAS Colloquia & Seminars
Speaker:
Dr.Jiayi Guo, Operations Research and Information Engineering,Cornell University
Inviter:
Title:
Smooth quasi-Newton methods for nonsmooth optimization
Time & Venue:
2017.12.8 10:00-11:00 Z311
Abstract:
Sporadic informal observations over several decades (and most recently in Lewis-Overton, 2013) suggest that quasi-Newton methods for smooth optimization can also work surprisingly well on nonsmooth functions. This talk explores this phenomenon from several perspectives. First, we compare experimentally the two most popular quasi-Newton updates, BFGS and SR1, in the nonsmooth setting. Secondly, we study how repeated BFGS updating at a single fixed point can serve as a separation oracle (for the subdifferential). Lastly, we show how Powell's original 1976 BFGS convergence proof for smooth convex functions in fact extends to some nonsmooth settings.