Efficient Minimization of Decomposable Submodular Functions
Abstract
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 subclass of submodular minimization problems that we call decomposable. Decomposable submodular functions are those that can be represented as sums of concave functions applied to modular functions. We develop an algorithm, SLG, that can efficiently minimize decomposable submodular functions with tens of thousands of variables. Our algorithm exploits recent results in smoothed convex minimization. We apply SLG to synthetic benchmarks and a joint classification-and-segmentation task, and show that it outperforms the state-of-the-art general purpose submodular minimization algorithms by several orders of magnitude.
Additional Information
©2010 Neural Information Processing Systems. This research was partially supported by NSF grant IIS-0953413, a gift from Microsoft Corporation and an Okawa Foundation Research Grant. Thanks to Alex Gittens and Michael McCoy for use of their TextonBoost implementation.Attached Files
Published - 4028-efficient-minimization-of-decomposable-submodular-functions.pdf
Files
Name | Size | Download all |
---|---|---|
md5:6bb059a1be75220464b195b68db9b3b4
|
347.5 kB | Preview Download |
Additional details
- Eprint ID
- 65823
- Resolver ID
- CaltechAUTHORS:20160331-164338717
- IIS-0953413
- NSF
- Microsoft Corporation
- Okawa Foundation
- Created
-
2016-03-31Created from EPrint's datestamp field
- Updated
-
2020-03-09Created from EPrint's last_modified field