Corpus ID: 5608979

On the Convergence Rate of Decomposable Submodular Function Minimization

@inproceedings{Nishihara2014OnTC,
  title={On the Convergence Rate of Decomposable Submodular Function Minimization},
  author={Robert Nishihara and Stefanie Jegelka and Michael I. Jordan},
  booktitle={NIPS},
  year={2014}
}
Submodular functions describe a variety of discrete problems in machine learning, signal processing, and computer vision. However, minimizing submodular functions poses a number of algorithmic challenges. Recent work introduced an easy-to-use, parallelizable algorithm for minimizing submodular functions that decompose as the sum of "simple" submodular functions. Empirically, this algorithm performs extremely well, but no theoretical analysis was given. In this paper, we show that the algorithm… Expand
Random Coordinate Descent Methods for Minimizing Decomposable Submodular Functions
TLDR
This paper uses random coordinate descent methods to obtain algorithms with faster linear convergence rates and cheaper iteration costs, and their algorithms converge in significantly fewer iterations. Expand
Quadratic Decomposable Submodular Function Minimization
TLDR
This work introduces a new convex optimization problem, termed quadratic decomposable submodular function minimization, and describes an objective that may be optimized via random coordinate descent methods and projections onto cones and establishes the linear convergence rate of the RCD algorithm. Expand
Fast Decomposable Submodular Function Minimization using Constrained Total Variation
TLDR
A modified convex problem requiring constrained version of the total variation oracles that can be solved with significantly fewer calls to the simple minimization oracles is considered. Expand
Decomposable Submodular Function Minimization via Maximum Flow
This paper bridges discrete and continuous optimization approaches for decomposable submodular function minimization, in both the standard and parametric settings. We provide improved running timesExpand
Quadratic Decomposable Submodular Function Minimization: Theory and Practice
TLDR
A new convex optimization problem, termed quadratic decomposable submodular function minimization (QDSFM), which allows to model a number of learning tasks on graphs and hypergraphs and two new applications of QDSFM are described: hypergraph-adapted PageRank and semi-supervised learning. Expand
Quadratic Decomposable Submodular Function Minimization: Theory and Practice
We introduce a new convex optimization problem, termed quadratic decomposable submodular function minimization (QDSFM), which allows to model a number of learning tasks on graphs and hypergraphs. TheExpand
Decomposable Submodular Function Minimization: Discrete and Continuous
TLDR
Improved running time estimates are provided for the state-of-the-art continuous algorithms for the decomposable submodular function minimization problem using combinatorial arguments and a systematic experimental comparison of the two types of methods is provided. Expand
The adaptive complexity of maximizing a submodular function
TLDR
The result implies that in the realizable case, where there is a true underlying function generating the data, Θ(log n) batches of adaptive samples are necessary and sufficient to approximately “learn to optimize” a monotone submodular function under a cardinality constraint. Expand
Efficient Minimization of Higher Order Submodular Functions using Monotonic Boolean Functions
TLDR
Novel mapping is defined that transform submodular functions of order $k$ into quadratic ones, which can be efficiently minimized in $O(n^3)$ time using a max-flow algorithm. Expand
Active-set Methods for Submodular Minimization Problems
TLDR
A new active-set algorithm for total variation denoising with the assumption of an oracle that solves the corresponding SFM problem is proposed, which performs local descent over ordered partitions and its ability to warm start considerably improves the performance of the algorithm. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 46 REFERENCES
Efficient Minimization of Decomposable Submodular Functions
TLDR
This paper develops an algorithm, SLG, that can efficiently minimize decomposable submodular functions with tens of thousands of variables, and applies it to synthetic benchmarks and a joint classification-and-segmentation task, and shows that it outperforms the state-of-the-art general purpose sub modular minimization algorithms by several orders of magnitude. Expand
A FASTER SCALING ALGORITHM FOR MINIMIZING SUBMODULAR FUNCTIONS∗
Combinatorial strongly polynomial algorithms for minimizing submodular functions have been developed by Iwata, Fleischer, and Fujishige (IFF) and by Schrijver. The IFF algorithm employs a scalingExpand
On fast approximate submodular minimization
TLDR
A fast approximate method to minimize arbitrary submodular functions and shows theoretical properties, and empirical results suggest significant speedups over minimum norm while retaining higher accuracies. Expand
A Submodular Function Minimization Algorithm Based on the Minimum-Norm Base ⁄
We consider an application of the minimum-norm-point algorithm to submodular function minimization. Although combinatorial polynomial algorithms for submodular function minimization (SFM) haveExpand
A faster strongly polynomial time algorithm for submodular function minimization
  • J. Orlin
  • Mathematics, Computer Science
  • Math. Program.
  • 2009
TLDR
A combinatorial algorithm that runs in O(n5EO  +  n6) time, where EO is the time to evaluate f(S) for some submodular function f defined on a set V with n elements is given. Expand
Minimizing a sum of submodular functions
  • V. Kolmogorov
  • Computer Science, Mathematics
  • Discret. Appl. Math.
  • 2012
TLDR
This work casts the problem of minimizing a function represented as a sum of submodular terms in an auxiliary graph in such a way that applying most existing SF algorithms would rely only on these subroutines, and shows how to improve its complexity in the case when the function contains cardinality-dependent terms. Expand
Learning with Submodular Functions: A Convex Optimization Perspective
  • F. Bach
  • Computer Science, Mathematics
  • Found. Trends Mach. Learn.
  • 2013
TLDR
In Learning with Submodular Functions: A Convex Optimization Perspective, the theory of submodular functions is presented in a self-contained way from a convex analysis perspective, presenting tight links between certain polyhedra, combinatorial optimization and convex optimization problems. Expand
Reflection methods for user-friendly submodular optimization
TLDR
This work proposes a new method that exploits existing decomposability of submodular functions, and solves both the continuous and discrete formulations of the problem, and therefore has applications in learning, inference, and reconstruction. Expand
The ellipsoid method and its consequences in combinatorial optimization
TLDR
The method yields polynomial algorithms for vertex packing in perfect graphs, for the matching and matroid intersection problems, for optimum covering of directed cuts of a digraph, and for the minimum value of a submodular set function. Expand
Local Search for Balanced Submodular Clusterings
TLDR
This paper shows that the results of Patkar and Narayanan can be applied to cases when the submodular function is derived from a bipartite object-feature graph, and moreover, in this case there is an efficient flow based algorithm for finding local improvements. Expand
...
1
2
3
4
5
...