A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
A New Randomized Primal-Dual Algorithm for Convex Optimization with Optimal Last Iterate Rates
[article]
2021
arXiv
pre-print
We develop a novel unified randomized block-coordinate primal-dual algorithm to solve a class of nonsmooth constrained convex optimization problems, which covers different existing variants and model settings from the literature. We prove that our algorithm achieves optimal 𝒪(n/k) and 𝒪(n^2/k^2) convergence rates (up to a constant factor) in two cases: general convexity and strong convexity, respectively, where k is the iteration counter and n is the number of block-coordinates. Our convergence
arXiv:2003.01322v3
fatcat:5falgb6kyndpvmfzcxhsq2zlha