论文标题
随机领域的模棱两可的学习：高斯过程和可声的有条件神经过程
Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
论文作者
论文摘要
由电场或流体流等物体的动机，我们研究了学习随机场的问题，即其样品像物理和工程中发生的样品一样的随机过程。考虑到一般的转换，例如旋转和反射，我们表明随机场的空间不变性需要推理模型是均等的。利用均衡性文献的最新进展，我们研究了两类模型中的均衡。首先，我们充分表征了高斯流程。其次，我们介绍了可传入的有条件神经过程（Steercnps），这是神经过程家族的全新，完全模棱两可的成员。在使用高斯流程矢量场，图像和现实世界中的天气数据的实验中，我们观察到，脱水可以显着提高先前模型的性能和均衡性，从而改善了转移学习任务的改进。
Motivated by objects such as electric fields or fluid streams, we study the problem of learning stochastic fields, i.e. stochastic processes whose samples are fields like those occurring in physics and engineering. Considering general transformations such as rotations and reflections, we show that spatial invariance of stochastic fields requires an inference model to be equivariant. Leveraging recent advances from the equivariance literature, we study equivariance in two classes of models. Firstly, we fully characterise equivariant Gaussian processes. Secondly, we introduce Steerable Conditional Neural Processes (SteerCNPs), a new, fully equivariant member of the Neural Process family. In experiments with Gaussian process vector fields, images, and real-world weather data, we observe that SteerCNPs significantly improve the performance of previous models and equivariance leads to improvements in transfer learning tasks.
