Decomposable Submodular Function Minimization: Discrete and Continuous
نویسندگان
چکیده
This paper investigates connections between discrete and continuous approaches for decomposable submodular function minimization. We provide improved running time estimates for the state-of-the-art continuous algorithms for the problem using combinatorial arguments. We also provide a systematic experimental comparison of the two types of methods, based on a clear distinction between level-0 and level-1 algorithms.
منابع مشابه
Efficient Minimization of Decomposable Submodular Functions
Many combinatorial problems arising in machine learning can be reduced to the problem of minimizing a submodular function. Submodular functions are a natural discrete analog of convex functions, and can be minimized in strongly polynomial time. Unfortunately, state-of-the-art algorithms for general submodular minimization are intractable for larger problems. In this paper, we introduce a novel ...
متن کاملRevisiting Decomposable Submodular Function Minimization with Incidence Relations
We introduce a new approach to decomposable submodular function minimization (DSFM) that exploits incidence relations. Incidence relations describe which variables effectively influence the component functions, and when properly utilized, they allow for improving the convergence rates of DSFM solvers. Our main results include the precise parametrization of the DSFM problem based on incidence re...
متن کاملOn the Convergence Rate of Decomposable Submodular Function Minimization
Submodular functions describe a variety of discrete problems in machine learn-ing, signal processing, and computer vision. However, minimizing submodularfunctions poses a number of algorithmic challenges. Recent work introduced aneasy-to-use, parallelizable algorithm for minimizing submodular functions thatdecompose as the sum of “simple” submodular functions. Empirically, this ...
متن کاملReflection methods for user-friendly submodular optimization
Recently, it has become evident that submodularity naturally captures widely occurring concepts in machine learning, signal processing and computer vision. Consequently, there is need for efficient optimization procedures for submodular functions, especially for minimization problems. While general submodular minimization is challenging, we propose a new method that exploits existing decomposab...
متن کاملSubmodular Function Minimization and Maximization in Discrete Convex Analysis
This paper sheds a new light on submodular function minimization and maximization from the viewpoint of discrete convex analysis. L-convex functions and M-concave functions constitute subclasses of submodular functions on an integer interval. Whereas L-convex functions can be minimized efficiently on the basis of submodular (set) function minimization algorithms, M-concave functions are identif...
متن کامل