Projective Splitting with Forward Steps only Requires Continuity

09/17/2018
by   Patrick R. Johnstone, et al.
0

A recent innovation in projective splitting algorithms for monotone operator inclusions has been the development of a procedure using two forward steps instead of the customary proximal steps for operators that are Lipschitz continuous. This paper shows that the Lipschitz assumption is unnecessary when the forward steps are performed in finite-dimensional spaces: a backtracking linesearch yields a convergent algorithm for operators that are merely continuous with full domain.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/19/2018

Projective Splitting with Forward Steps: Asynchronous and Block-Iterative Operator Splitting

This work is concerned with the classical problem of finding a zero of a...
research
11/04/2020

Convolutional Proximal Neural Networks and Plug-and-Play Algorithms

In this paper, we introduce convolutional proximal neural networks (cPNN...
research
02/24/2019

Single-Forward-Step Projective Splitting: Exploiting Cocoercivity

This work describes a new variant of projective splitting in which cocoe...
research
02/08/2023

Extragradient-Type Methods with 𝒪(1/k) Convergence Rates for Co-Hypomonotone Inclusions

In this paper, we develop two “Nesterov's accelerated” variants of the w...
research
04/19/2018

BISTA: a Bregmanian proximal gradient method without the global Lipschitz continuity assumption

The problem of minimization of a separable convex objective function has...
research
11/08/2022

Frugal and Decentralised Resolvent Splittings Defined by Nonexpansive Operators

Frugal resolvent splittings are a class of fixed point algorithms for fi...
research
07/19/2023

Deep Operator Network Approximation Rates for Lipschitz Operators

We establish universality and expression rate bounds for a class of neur...

Please sign up or login with your details

Forgot password? Click here to reset