Skip to yearly menu bar Skip to main content


Alternating Minimizations Converge to Second-Order Optimal Solutions

Qiuwei Li · Zhihui Zhu · Gongguo Tang

Pacific Ballroom #110

Keywords: [ Non-convex Optimization ] [ Matrix Factorization ]


This work studies the second-order convergence for both standard alternating minimization and proximal alternating minimization. We show that under mild assumptions on the (nonconvex) objective function, both algorithms avoid strict saddles almost surely from random initialization. Together with known first-order convergence results, this implies both algorithms converge to a second-order stationary point. This solves an open problem for the second-order convergence of alternating minimization algorithms that have been widely used in practice to solve large-scale nonconvex problems due to their simple implementation, fast convergence, and superb empirical performance.

Live content is unavailable. Log in and register to view live content