A variational approximate posterior for the deep Wishart process

Abstract

Recent work introduced deep kernel processes as an entirely kernel-based alternative to NNs (Aitchison et al. 2020). Deep kernel processes flexibly learn good top-layer representations by alternately sampling the kernel from a distribution over positive semi-definite matrices and performing nonlinear transformations. A particular deep kernel process, the deep Wishart process (DWP), is of particular interest because its prior can be made equivalent to deep Gaussian process (DGP) priors for kernels that can be expressed entirely in terms of Gram matrices. However, inference in DWPs has not yet been possible due to the lack of sufficiently flexible distributions over positive semi-definite matrices. Here, we give a novel approach to obtaining flexible distributions over positive semi-definite matrices by generalising the Bartlett decomposition of the Wishart probability density. We use this new distribution to develop an approximate posterior for the DWP that includes dependency across layers. We develop a doubly-stochastic inducing-point inference scheme for the DWP and show experimentally that inference in the DWP can improve performance over doing inference in a DGP with the equivalent prior.

arXiv commentAccepted for publication at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021). 23 pages

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Deep Neural Networks as Gaussian Processes
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
• Deep Convolutional Networks as shallow Gaussian Processes
• Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference
• Generalised Wishart Processes
• Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
• Stochastic Differential Equations with Variational Wishart Diffusions
• Why bigger is not always better: on finite and infinite neural networks
• Deep kernel processes