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 co...
Submodular function minimization is a polynomially-solvable combinatorial problem. Unfortunately the best known general-purpose algorithms have high-order polynomial time complexi...
We introduce several generalizations of classical computer science problems obtained by replacing simpler objective functions with general submodular functions. The new problems i...
Submodular maximization generalizes many important problems including Max Cut in directed/undirected graphs and hypergraphs, certain constraint satisfaction problems and maximum f...
We describe an energy minimization algorithm for functions defined on 4-connected lattices, of the type usually encountered in problems involving images. Such functions are often ...