Simple Map Inference Via Low-Rank Relaxations
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014)(2014)
摘要
We focus on the problem of maximum a posteriori (MAP) inference in Markov random fields with binary variables and pairwise interactions. For this common subclass of inference tasks, we consider low-rank relaxations that interpolate between the discrete problem and its full-rank semidefinite relaxation. We develop new theoretical bounds studying the effect of rank, showing that as the rank grows, the relaxed objective increases but saturates, and that the fraction in objective value retained by the rounded discrete solution decreases. In practice, we show two algorithms for optimizing the low-rank objectives which are simple to implement, enjoy ties to the underlying theory, and outperform existing approaches on benchmark MAP inference tasks.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络