Reflection methods for user-friendly submodular optimization
@inproceedings{Jegelka2013ReflectionMF, title={Reflection methods for user-friendly submodular optimization}, author={S. Jegelka and Francis R. Bach and S. Sra}, booktitle={NIPS}, year={2013} }
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 decomposability of submodular functions. In contrast to previous approaches, our method is neither approximate… CONTINUE READING
Figures, Tables, and Topics from this paper
64 Citations
Active-set Methods for Submodular Minimization Problems
- Mathematics, Computer Science
- J. Mach. Learn. Res.
- 2017
- 5
- Highly Influenced
- PDF
Learning with Submodular Functions: A Convex Optimization Perspective
- Computer Science, Mathematics
- Found. Trends Mach. Learn.
- 2013
- 325
- PDF
Quadratic Decomposable Submodular Function Minimization: Theory and Practice
- 2020
- Highly Influenced
- PDF
Playing with Duality: An overview of recent primal?dual approaches for solving large-scale optimization problems
- Computer Science, Mathematics
- IEEE Signal Process. Mag.
- 2015
- 76
- PDF
Min Norm Point Algorithm for Higher Order MRF-MAP Inference
- Mathematics, Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 10
- PDF
Quadratic Decomposable Submodular Function Minimization: Theory and Practice
- Computer Science, Mathematics
- J. Mach. Learn. Res.
- 2020
- 6
- Highly Influenced
- PDF
From MAP to Marginals: Variational Inference in Bayesian Submodular Models
- Computer Science, Mathematics
- NIPS
- 2014
- 66
- PDF
References
SHOWING 1-10 OF 67 REFERENCES
MRF Energy Minimization and Beyond via Dual Decomposition
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2011
- 316
- Highly Influential
- PDF
Learning with Submodular Functions: A Convex Optimization Perspective
- Computer Science, Mathematics
- Found. Trends Mach. Learn.
- 2013
- 325
- PDF
Efficient Minimization of Decomposable Submodular Functions
- Computer Science, Mathematics
- NIPS
- 2010
- 116
- Highly Influential
- PDF
A study of Nesterov's scheme for Lagrangian decomposition and MAP labeling
- Mathematics, Computer Science
- CVPR 2011
- 2011
- 63
- Highly Influential
- PDF
Proximal Methods for Hierarchical Sparse Coding
- Computer Science, Mathematics
- J. Mach. Learn. Res.
- 2011
- 313
- PDF
Proximal Splitting Methods in Signal Processing
- Computer Science, Mathematics
- Fixed-Point Algorithms for Inverse Problems in Science and Engineering
- 2011
- 2,052
- Highly Influential
- PDF
Convergence Rate Analysis of MAP Coordinate Minimization Algorithms
- Computer Science, Mathematics
- NIPS
- 2012
- 30
- PDF
Efficient solutions to relaxations of combinatorial problems with submodular penalties via the Lovász extension and non-smooth convex optimization
- Mathematics, Computer Science
- SODA '07
- 2007
- 32