Timezone: »

Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
Peter Holderrieth · Michael Hutchinson · Yee-Whye Teh

Thu Jul 22 08:35 PM -- 08:40 PM (PDT) @

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.

Author Information

Peter Holderrieth (University of Oxford)
Michael Hutchinson (University of Oxford)
Yee-Whye Teh (Oxford and DeepMind)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors