We extend the work of Narasimhan and Bilmes [30] for minimizing set functions representable as a difference between sub- modular functions. Similar to [30], our new algorithms are guaranteed to monotonically reduce the objective function at every step. We empirically and theoretically show that the per-iteration cost of our algorithms is much less than [30], and our algorithms can be used to efficiently minimize a difference between submodular functions under various combinatorial constraints, a problem not pre- viously addressed. We provide computational bounds and a hardness result on the mul- tiplicative inapproximability of minimizing the difference between submodular functions. We show, however, that it is possible to give worst-case additive bounds by providing a polynomial time computable lower-bound on the minima. Finally we show how a number of machine learning problems can be modeled as minimizing the difference between submodular functions. We experimentally show the validity of our algorithms by testing them on the problem of feature selection with submodular cost features.

本研究扩展了Narasimhan和Bilmes的工作，提出了基于子模函数差别最小化的新算法，该算法能有效地解决多种组合约束的问题，并且能够用于许多机器学习问题中，它在性能上优于现有的算法。

近似最小化次模函数差的算法及应用