Combinatorial Preconditioners for Proximal Algorithms on Graphs

01/16/2018
by   Thomas Möllenhoff, et al.
0

We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners. Such combinatorial preconditioners arise from partitioning the graph into forests. We prove that certain decompositions lead to a theoretically optimal condition number. We also show how ideal decompositions can be realized using matroid partitioning and propose efficient greedy variants thereof for large-scale problems. Coupled with specialized solvers for the resulting scaled proximal subproblems, the preconditioned algorithm achieves competitive performance in machine learning and vision applications.

READ FULL TEXT
research
02/27/2020

Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning

Structured convex optimization on weighted graphs finds numerous applica...
research
05/18/2019

Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching

We propose a scalable Gromov-Wasserstein learning (S-GWL) method and est...
research
06/12/2020

Sallow: a heuristic algorithm for treedepth decompositions

We describe a heuristic algorithm for computing treedepth decompositions...
research
01/08/2013

A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions

We propose an algorithmic framework for convex minimization problems of ...
research
05/14/2013

Optimization with First-Order Surrogate Functions

In this paper, we study optimization methods consisting of iteratively m...
research
12/05/2018

Hard combinatorial problems and minor embeddings on lattice graphs

Today, hardware constraints are an important limitation on quantum adiab...
research
02/16/2022

A Polyhedral Study of Lifted Multicuts

Fundamental to many applications in data analysis are the decompositions...

Please sign up or login with your details

Forgot password? Click here to reset