@kirk86

Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights

, and . (2020)cite arxiv:2002.04033Comment: 12 pages main paper, 13 pages appendix.

Abstract

Probabilistic neural networks are typically modeled with independent weight priors, which do not capture weight correlations in the prior and do not provide a parsimonious interface to express properties in function space. A desirable class of priors would represent weights compactly, capture correlations between weights, facilitate calibrated reasoning about uncertainty, and allow inclusion of prior knowledge about the function space such as periodicity or dependence on contexts such as inputs. To this end, this paper introduces two innovations: (i) a Gaussian process-based hierarchical model for network weights based on unit embeddings that can flexibly encode correlated weight structures, and (ii) input-dependent versions of these weight priors that can provide convenient ways to regularize the function space through the use of kernels defined on contextual inputs. We show these models provide desirable test-time uncertainty estimates on out-of-distribution data, demonstrate cases of modeling inductive biases for neural networks with kernels which help both interpolation and extrapolation from training data, and demonstrate competitive predictive performance on an active learning benchmark.

Description

[2002.04033] Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights

Links and resources

URL:
BibTeX key:
karaletsos2020hierarchical
search on:

Comments and Reviews  
(0)

There is no review or comment yet. You can write one!

Tags


Cite this publication