Timezone: »

Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization
Qunwei Li · Yi Zhou · Yingbin Liang · Pramod K Varshney

Tue Aug 08 01:30 AM -- 05:00 AM (PDT) @ Gallery #131

In this work, we investigate the accelerated proximal gradient method for nonconvex programming (APGnc). The method compares between a usual proximal gradient step and a linear extrapolation step, and accepts the one that has a lower function value to achieve a monotonic decrease. In specific, under a general nonsmooth and nonconvex setting, we provide a rigorous argument to show that the limit points of the sequence generated by APGnc are critical points of the objective function. Then, by exploiting the Kurdyka-Lojasiewicz (KL) property for a broad class of functions, we establish the linear and sub-linear convergence rates of the function value sequence generated by APGnc. We further propose a stochastic variance reduced APGnc (SVRG-APGnc), and establish its linear convergence under a special case of the KL property. We also extend the analysis to the inexact version of these methods and develop an adaptive momentum strategy that improves the numerical performance.

Author Information

Qunwei Li (Syracuse University)
Yi Zhou (Syracuse University)
Yingbin Liang
Pramod K Varshney (Syracuse University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors