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 algorithm
This paper presents a new simple algorithm for minimizing submodular functions. For integer valued s...
We extend the work of Narasimhan and Bilmes [30] for minimizing set functions representable as a dif...
Building on recent results for submodular minimization with combinatorial constraints, and on online...
This paper investigates connections between discrete and continuous approaches for decomposable subm...
This paper investigates connections between discrete and continuous approaches for decomposable subm...
Submodular functions often arise in various fields of operations research including discrete optimiz...
Many combinatorial problems arising in machine learning can be reduced to the problem of minimizing ...
Presented at the Georgia Tech Algorithms & Randomness Center workshop: Modern Aspects of Submodular...
Many combinatorial problems arising in machine learning can be reduced to the problem of minimizing ...
Presented on October 17, 2016 at 11:00 a.m. in the Klaus Advanced Computing Building, Room 1116E.Ali...
This paper presents the first combinatorial polynomial-time algorithm for minimizing submodular func...
Continuous submodular functions are a category of generally non-convex/non-concave functions with a ...
Submodular functions occur in many combinatorial optimisation problems and a number of polynomial-ti...
Submodular functions occur in many combinatorial optimisation problems and a number of polynomial-ti...
We present a practical and powerful new framework for both unconstrained and constrained submodular ...
This paper presents a new simple algorithm for minimizing submodular functions. For integer valued s...
We extend the work of Narasimhan and Bilmes [30] for minimizing set functions representable as a dif...
Building on recent results for submodular minimization with combinatorial constraints, and on online...
This paper investigates connections between discrete and continuous approaches for decomposable subm...
This paper investigates connections between discrete and continuous approaches for decomposable subm...
Submodular functions often arise in various fields of operations research including discrete optimiz...
Many combinatorial problems arising in machine learning can be reduced to the problem of minimizing ...
Presented at the Georgia Tech Algorithms & Randomness Center workshop: Modern Aspects of Submodular...
Many combinatorial problems arising in machine learning can be reduced to the problem of minimizing ...
Presented on October 17, 2016 at 11:00 a.m. in the Klaus Advanced Computing Building, Room 1116E.Ali...
This paper presents the first combinatorial polynomial-time algorithm for minimizing submodular func...
Continuous submodular functions are a category of generally non-convex/non-concave functions with a ...
Submodular functions occur in many combinatorial optimisation problems and a number of polynomial-ti...
Submodular functions occur in many combinatorial optimisation problems and a number of polynomial-ti...
We present a practical and powerful new framework for both unconstrained and constrained submodular ...
This paper presents a new simple algorithm for minimizing submodular functions. For integer valued s...
We extend the work of Narasimhan and Bilmes [30] for minimizing set functions representable as a dif...
Building on recent results for submodular minimization with combinatorial constraints, and on online...