Solving composite minimization problems arising in statistics and engineering, with applications to phase retrieval

Neyman Seminar
Berkeley-Stanford Joint Colloquium at Berkeley
Apr 3, 2018 4:00pm to 5:00pm
60 Evans Hall
Happening As Scheduled
We consider minimization of stochastic functionals that are compositions of a (potentially) non-smooth convex function h and smooth function c. We develop two stochastic methods--a stochastic prox-linear algorithm and a stochastic (generalized) sub- gradient procedure--and prove that, under mild technical conditions, each converges to stationary points of the stochastic objective. Additionally,...
John C. Duchi, Stanford University