Extensions to the Proximal Distance of Method of Constrained Optimization
The current paper studies the problem of minimizing a loss f(x) subject to constraints of the form Dx∈ S, where S is a closed set, convex or not, and D is a fusion matrix. Fusion constraints can capture smoothness, sparsity, or more general constraint patterns. To tackle this generic class of problems, we combine the Beltrami-Courant penalty method of optimization with the proximal distance principle. The latter is driven by minimization of penalized objectives f(x)+ρ/2dist(Dx,S)^2 involving large tuning constants ρ and the squared Euclidean distance of Dx from S. The next iterate x_n+1 of the corresponding proximal distance algorithm is constructed from the current iterate x_n by minimizing the majorizing surrogate function f(x)+ρ/2Dx-𝒫_S(Dx_n)^2. For fixed ρ and convex f(x) and S, we prove convergence, provide convergence rates, and demonstrate linear convergence under stronger assumptions. We also construct a steepest descent (SD) variant to avoid costly linear system solves. To benchmark our algorithms, we adapt the alternating direction method of multipliers (ADMM) and compare on extensive numerical tests including problems in metric projection, convex regression, convex clustering, total variation image denoising, and projection of a matrix to one that has a good condition number. Our experiments demonstrate the superior speed and acceptable accuracy of the steepest variant on high-dimensional problems. Julia code to replicate all of our experiments can be found at https://github.com/alanderos91/ProximalDistanceAlgorithms.jl.
READ FULL TEXT