Pseudo-Bayesian Learning via Direct Loss Minimization with Applications to Sparse Gaussian Process Models
Pseudo-Bayesian Learning via Direct Loss Minimization with Applications to Sparse Gaussian Process Models
复制标题
DOI：
--
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Rishit Sheth;R. Khardon
中科院分区：
文献类型：
--
作者：
Rishit Sheth;R. Khardon
我们建议近似贝叶斯算法应该优化直接从损失导出的新标准，以计算它们的近似后验，我们将其称为伪后验。与优化对数边际似然下限的标准变分推理不同，可以分析新算法以通过伪后验为预测提供损失保证。我们的标准可用于导出新的稀疏高斯过程算法，该算法具有适用于各种可能性的误差保证。
We propose that approximate Bayesian algorithms should optimize a new criterion, directly derived from the loss, to calculate their approximate posterior which we refer to as pseudoposterior. Unlike standard variational inference which optimizes a lower bound on the log marginal likelihood, the new algorithms can be analyzed to provide loss guarantees on the predictions with the pseudo-posterior. Our criterion can be used to derive new sparse Gaussian process algorithms that have error guarantees applicable to various likelihoods.