First-order primal-dual methods for nonsmooth nonconvex optimisation
arXiv:1910.00115 · doi:10.1007/978-3-030-03009-4_93-1
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.
References in corpus (6)
- Relaxed Gauss-Newton methods with applications to electrical impedance tomography
- A Generalization of the Chambolle-Pock Algorithm to Banach Spaces with Applications to Inverse Problems
- Primal-dual block-proximal splitting for a class of non-convex problems
- Introduction to Nonsmooth Analysis and Optimization
- First- and Second-Order Analysis for Optimization Problems with Manifold-Valued Constraints
- Fenchel Duality Theory and A Primal-Dual Algorithm on Riemannian Manifolds