Efficient Minimization of Decomposable Submodular Functions

Details Efficient Minimization of Decomposable Submodular Functions Efficient Minimization of Decomposable Submodular Functions

2010-10-26

arxiv.org/abs/1010.5511v1

Computer Science

Learning

Expanded version of paper for Neural Information Processing Systems 2010

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Efficient Minimization of Decomposable Submodular Functions does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Efficient Minimization of Decomposable Submodular Functions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Efficient Minimization of Decomposable Submodular Functions will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-484141