Generalized Expectation Criteria
作者： Gregory Druck , Andrew McCallum , Gideon Mann
DOI:
关键词: Estimation theory 、 Mathematics 、 Mathematical optimization 、 Leverage (statistics)
摘要: This note describes generalized expectation (GE) criteria, a framework for incorporating preferences about model expectations into parameter estimation objective functions. We discuss relations to other methods, various learning paradigms it supports, and applications that can leverage its flexibility.
gregorydruck.name 参考文章(3)
Gregory Druck, Gideon Mann, Andrew McCallum, Reducing Annotation Effort Using Generalized Expectation Criteria Defense Technical Information Center. ,(2007) , 10.21236/ADA493136
Gideon S. Mann, Andrew McCallum, Simple, robust, scalable semi-supervised learning via expectation regularization international conference on machine learning. pp. 593- 600 ,(2007) , 10.1145/1273496.1273571
Gregory Druck, Andrew McCallum, Gideon Mann, Leveraging Existing Resources using Generalized Expectation Criteria ,(2007)