An information theoretic analysis of maximum likelihood mixture estimation for exponential families
An information theoretic analysis of maximum likelihood mixture estimation for exponential families
复制标题
指数族最大似然混合估计的信息论分析
DOI:
10.1145/1015330.1015431
复制
发表时间:
2004
期刊:
影响因子:
--
通讯作者:
S. Merugu
中科院分区:
文献类型:
--
作者:
A. Banerjee;I. Dhillon;Joydeep Ghosh;S. Merugu
An important task in unsupervised learning is maximum likelihood mixture estimation (MLME) for exponential families. In this paper, we prove a mathematical equivalence between this MLME problem and the rate distortion problem for Bregman divergences. We also present new theoretical results in rate distortion theory for Bregman divergences. Further, an analysis of the problems as a trade-off between compression and preservation of information is presented that yields the information bottleneck method as an interesting special case.
DOI:
10.1137/1.9781611972740.22
发表时间:
2005-12
期刊:
J. Mach. Learn. Res.
影响因子:
--
作者:
A. Banerjee;S. Merugu;I. Dhillon;Joydeep Ghosh
通讯作者:
A. Banerjee;S. Merugu;I. Dhillon;Joydeep Ghosh