Accurate Bayesian Data Classification Without Hyperparameter Cross-Validation
Accurate Bayesian Data Classification Without Hyperparameter Cross-Validation
复制标题
无需超参数交叉验证即可进行准确的贝叶斯数据分类
DOI:
10.1007/s00357-019-09316-6
复制
发表时间:
2019
影响因子:
2
通讯作者:
Sheikh M
中科院分区:
文献类型:
--
作者:
Sheikh M
We extend the standard Bayesian multivariate Gaussian generative data classifier by considering a generalization of the conjugate, normal-Wishart prior distribution, and by deriving the hyperparameters analytically via evidence maximization. The behaviour of the optimal hyperparameters is explored in the high-dimensional data regime. The classification accuracy of the resulting generalized model is competitive with state-of-the art Bayesian discriminant analysis methods, but without the usual computational burden of cross-validation.
登录
查看更多内容
影响因子:
2.3
作者:
A. Shalabi;M. Inoue;Johnathan Watkins;E. de Rinaldis;A. Coolen
通讯作者:
A. Coolen
影响因子:
2.9
作者:
MacKay, DJC
通讯作者:
MacKay, DJC
影响因子:
2.5
作者:
D. Keehn
通讯作者:
D. Keehn
DOI:
--
发表时间:
1999
期刊:
影响因子:
--
作者:
P. Brown;T. Fearn;M. Haque
通讯作者:
M. Haque
影响因子:
2
作者:
HUBERT, L;ARABIE, P
通讯作者:
ARABIE, P