First-order primal-dual methods for nonsmooth nonconvex optimisation
Optimization and Control
2021-08-03 v3
Abstract
We provide an overview of primal-dual algorithms for nonsmooth and non-convex-concave saddle-point problems. This flows around a new analysis of such methods, using Bregman divergences to formulate simplified conditions for convergence.
Cite
@article{arxiv.1910.00115,
title = {First-order primal-dual methods for nonsmooth nonconvex optimisation},
author = {Tuomo Valkonen},
journal= {arXiv preprint arXiv:1910.00115},
year = {2021}
}