On the Q-linear Convergence of a Majorized Proximal ADMM for Convex Composite Programming and Its Applications

[TMCSC]

July 22, 2020  14:30-15:30

腾讯会议(线上)


SPEAKER

张立卫 (大连理工大学)

ABSTRACT

This work aims to study the convergence rate of a majorized alternating direction method of multiplier with indefinite proximal terms (iPADMM) for solving linearly constrained convex composite optimization problems. We establish the Q-linear rate convergence theorem for 2-block majorized iPADMM under mild conditions. Based on this result, the convergence rate analysis of symmetric Gaussian-Seidel based majorized ADMM, which is designed for solving multi-block composite convex optimization problems, are given. We apply the majorized iPADMM to solve three types of regularized logistic regression problems: constrained regression, fused lasso and overlapping group lasso. The efficiency of majorized iPADMM are demonstrated on both simulation experiments and real data sets. (This is a joint work with Ning Zhang, Jia Wu)

ORGANIZERS

黄南京(四川大学)

寇     辉(四川大学)

连     增(四川大学)

张德学(四川大学)

张伟年(四川大学)

SUPPORTED BY

国家天元数学西南中心

四川大学数学学院

VIDEO

  • On the Q-linear Convergence of a Majorized Proximal ADMM for Convex Composite Programming and Its Applications
  • 14:30 - 15:30, 2020-07-22 at 腾讯会议(线上)
  • 张立卫(大连理工大学)