Math @ Duke
|
Publications [#361343] of Jianfeng Lu
Papers Published
- Chen, Z; Li, Y; Lu, J, On the global convergence of randomized coordinate gradient descent for
non-convex optimization
(January, 2021)
(last updated on 2024/04/23)
Abstract: In this work, we analyze the global convergence property of coordinate
gradient descent with random choice of coordinates and stepsizes for non-convex
optimization problems. Under generic assumptions, we prove that the algorithm
iterate will almost surely escape strict saddle points of the objective
function. As a result, the algorithm is guaranteed to converge to local minima
if all saddle points are strict. Our proof is based on viewing coordinate
descent algorithm as a nonlinear random dynamical system and a quantitative
finite block analysis of its linearization around saddle points.
|
|
dept@math.duke.edu
ph: 919.660.2800
fax: 919.660.2821
| |
Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320
|
|