`

Timezone: »

 
Poster
Adaptive Primal-Dual Splitting Methods for Statistical Learning and Image Processing
Tom Goldstein · Min Li · Xiaoming Yuan

Mon Dec 07 04:00 PM -- 08:59 PM (PST) @ 210 C #91 #None
in Poster Session »

The alternating direction method of multipliers (ADMM) is an important tool for solving complex optimization problems, but it involves minimization sub-steps that are often difficult to solve efficiently. The Primal-Dual Hybrid Gradient (PDHG) method is a powerful alternative that often has simpler substeps than ADMM, thus producing lower complexity solvers. Despite the flexibility of this method, PDHG is often impractical because it requires the careful choice of multiple stepsize parameters. There is often no intuitive way to choose these parameters to maximize efficiency, or even achieve convergence. We propose self-adaptive stepsize rules that automatically tune PDHG parameters for optimal convergence. We rigorously analyze our methods, and identify convergence rates. Numerical experiments show that adaptive PDHG has strong advantages over non-adaptive methods in terms of both efficiency and simplicity for the user.

[ PDF] 

Author Information

Tom Goldstein (University of Maryland)
Min Li (Southeast University)
Xiaoming Yuan (Hong Kong Baptist University)

More from the Same Authors