作者
Alan L Yuille, Anand Rangarajan
发表日期
2001
期刊
Advances in neural information processing systems
卷号
14
简介
We introduce the Concave-Convex procedure (CCCP) which con (cid: 173) structs discrete time iterative dynamical systems which are guar (cid: 173) anteed to monotonically decrease global optimization/energy func (cid: 173) tions. It can be applied to (almost) any optimization problem and many existing algorithms can be interpreted in terms of CCCP. In particular, we prove relationships to some applications of Legendre transform techniques. We then illustrate CCCP by applications to Potts models, linear assignment, EM algorithms, and Generalized Iterative Scaling (GIS). CCCP can be used both as a new way to understand existing optimization algorithms and as a procedure for generating new algorithms.
引用总数
学术搜索中的文章
AL Yuille, A Rangarajan - Advances in neural information processing systems, 2001