论文标题
神经过程中的不确定性
Uncertainty in Neural Processes
论文作者
论文摘要
我们探讨了建筑和训练客观选择对概率条件生成模型中摊销后验预测推断的影响。我们的目标是与文献中最近的趋势相对应，该趋势强调了在调理数据量较大时获得良好样本的重点。相反，我们将注意力集中在调理数据量较小的情况下。我们重点介绍了特定的体系结构和客观选择，这些选择会导致这种低数据制度的定性和定量改进。具体而言，我们探讨了合并操作员和变异家族的选择对神经过程中后质量的影响。从我们新的神经过程架构中得出的上后验预测样本通过图像完成/镶嵌实验证明。
We explore the effects of architecture and training objective choice on amortized posterior predictive inference in probabilistic conditional generative models. We aim this work to be a counterpoint to a recent trend in the literature that stresses achieving good samples when the amount of conditioning data is large. We instead focus our attention on the case where the amount of conditioning data is small. We highlight specific architecture and objective choices that we find lead to qualitative and quantitative improvement to posterior inference in this low data regime. Specifically we explore the effects of choices of pooling operator and variational family on posterior quality in neural processes. Superior posterior predictive samples drawn from our novel neural process architectures are demonstrated via image completion/in-painting experiments.
