BriefGPT.xyz
Mar, 2018
无眼泪的DAGs:结构学习的连续优化
DAGs with NO TEARS: Smooth Optimization for Structure Learning
HTML
PDF
Xun Zheng, Bryon Aragam, Pradeep Ravikumar, Eric P. Xing
TL;DR
本文提出了一种基于优化问题的连续方法,来解决结构学习问题,避免了组合约束,并有效地提高算法效率。该方法在没有强加任何结构假设的情况下,优于其它现有方法。
Abstract
Estimating the structure of
directed acyclic graphs
(DAGs, also known as
bayesian networks
) is a challenging problem since the search space of DAGs is combinatorial and scales superexponentially with the number o
→