Linear Convergence of the Proximal Incremental Aggregated Gradient Method under Quadratic Growth Condition
arXiv:1702.08166
Abstract
Under the strongly convex assumption, several recent works studied the global linear convergence rate of the proximal incremental aggregated gradient (PIAG) method for minimizing the sum of a large number of smooth component functions and a non-smooth convex function. In this paper, under \textsl{the quadratic growth condition}--a strictly weaker condition than the strongly convex assumption, we derive a new global linear convergence rate result, which implies that the PIAG method attains global linear convergence rates in both the function value and iterate point errors. The main idea behind is to construct a certain Lyapunov function.
9 pages
References in corpus (4)
- Analysis and Implementation of an Asynchronous Optimization Algorithm for the Parameter Server
- New Analysis of Linear Convergence of Gradient-type Methods via Unifying Error Bound Conditions
- Linearly Convergent Away-Step Conditional Gradient for Non-strongly Convex Functions
- A Stronger Convergence Result on the Proximal Incremental Aggregated Gradient Method