Fast copula variational inference
Fast copula variational inference
复制标题
快速 copula 变分推理
DOI：
10.1080/0952813x.2021.1871970
复制
发表时间：
2021-01
影响因子：
2.2
通讯作者：
李熙铭
中科院分区：
文献类型：
--
作者：
迟晋进;欧阳继红;张昂;王新华;李熙铭
ABSTRACT Mean-field variational inference, built on fully factorisations, can be efficiently solved; however, it ignores the dependencies between latent variables, resulting in lower performance. To address this, the copula variational inference (CVI) method is proposed by using the well-established copulas to effectively capture posterior dependencies, leading to better approximations. However, it suffers from a computational issue, where the optimisation for big models with massive latent variables is quite time-consuming. This is mainly caused by the expensive sampling when forming noisy Monte Carlo gradients in CVI. For CVI speedup, in this paper we propose a novel fast CVI (abbr. FCVI). In FCVI, we derive the gradient of CVI objective by an expectation of the mean-field factorisation. Therefore, we can achieve a much efficient sampling from the -dimensional mean-field factorisation, enabling to reduce the sampling complexity from to . To evaluate FCVI, we compare it against baseline methods on modelling performance and runtime. Experimental results demonstrate that FCVI is on a par with CVI, but runs much faster.
登录
查看更多内容
影响因子：
3.7
作者：
T. Burr
通讯作者：
T. Burr
DOI：
--
发表时间：
2012-06
期刊：
--
影响因子：
--
作者：
J. Paisley;D. Blei;Michael I. Jordan
通讯作者：
J. Paisley;D. Blei;Michael I. Jordan
影响因子：
3.1
作者：
KRACKHARDT, D
通讯作者：
KRACKHARDT, D
影响因子：
1.9
作者：
C. Genest;H. Gerber;M. Goovaerts;R. Laeven
通讯作者：
C. Genest;H. Gerber;M. Goovaerts;R. Laeven
影响因子：
2.2
作者：
Shaobo Han;X. Liao;D. Dunson;L. Carin
通讯作者：
Shaobo Han;X. Liao;D. Dunson;L. Carin