lecture image Computational Mathematics Seminar Series
Deterministic and Stochastic ADMM for Structured Convex Optimization
Jianchao Bai, Xi’an Jiaotong University
Digital Media Center 1034
September 04, 2018 - 03:30 pm

The Alternating Direction Method of Multipliers (ADMM) has a long history, but its algorithmic idea can be still used to design new algorithms for the application examples involving big-data. In this talk, we show our recent work about two kinds of deterministic ADMMs and a family of stochastic ADMM for solving structured convex optimization. We also present the convergence complexity of these ADMM-type algorithms. Several further questions are discussed finally.

Speaker's Bio:

Jianchao Bai received his M.S. degree from the College of Mathematics & Computational Science at Guilin Univeristy of Electronic Technology in 2015, and he will receive his Ph. D. degree from the School of Mathematics & Statistics at Xi’an Jiaotong University in 2018. His research interest includes low-rank approximation, first-order numerical algorithms and their applications in signal processing, statistics/machine learning.  


This lecture has refreshments @ 03:00 pm