Random Coordinate Descent Methods for Minimizing Decomposable Submodular Functions

Abstract

Submodular function minimization is a fundamental optimization problem that arises in several applications in machine learning and computer vision. The problem is known to be solvable in polynomial time, but general purpose algorithms have high running times and are unsuitable for large-scale problems. Recent work have used convex optimization techniques to obtain very practical algorithms for minimizing functions that are sums of ``simple" functions. In this paper, we use random coordinate descent methods to obtain algorithms with faster linear convergence rates and cheaper iteration costs. Compared to alternating projection methods, our algorithms do not rely on full-dimensional vector operations and they converge in significantly fewer iterations.

References in corpus (1)

• Efficient Minimization of Decomposable Submodular Functions

Cited by in corpus (7)

• Signal Processing on Higher-Order Networks: Livin' on the Edge ... and Beyond
• Revisiting Decomposable Submodular Function Minimization with Incidence Relations
• Decomposable Submodular Function Minimization via Maximum Flow
• Fast Decomposable Submodular Function Minimization using Constrained Total Variation
• Quadratic Decomposable Submodular Function Minimization: Theory and Practice (Computation and Analysis of PageRank over Hypergraphs)
• On the Hardness of Massively Parallel Computation
• Augmented Sparsifiers for Generalized Hypergraph Cuts with Applications to Decomposable Submodular Function Minimization