paper-with-me

홈 › Papers

Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights

2020-02-10 · NeurIPS 2020 12 · Theofanis Karaletsos, Thang D. Bui

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.

📄 PDF Abstract BibTeX arXiv:2002.04033

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

Varying-coefficient models with isotropic Gaussian process priors

2015-08-28 · Matthias Bussas, Christoph Sawade, Tobias Scheffer, Niels Landwehr

We study learning problems in which the conditional distribution of the output given the input varies as a function of additional task variables. In varying-coefficient models with Gaussian process priors, a Gaussian pro…

Bayesian Inference

Hybrid Bayesian Neural Networks with Functional Probabilistic Layers

2021-07-14 · Daniel T. Chang

Bayesian neural networks provide a direct and natural way to extend standard deep neural networks to support probabilistic deep learning through the use of probabilistic layers that, traditionally, encode weight (and bia…

Bayesian InferenceGaussian ProcessesProbabilistic Deep LearningVariational Inference

Variational EP with Probabilistic Backpropagation for Bayesian Neural Networks

2023-03-02 · Kehinde Olobatuyi

I propose a novel approach for nonlinear Logistic regression using a two-layer neural network (NN) model structure with hierarchical priors on the network weights. I present a hybrid of expectation propagation called Var…

regression

BNNpriors: A library for Bayesian neural network inference with different prior distributions

2021-05-14 · Vincent Fortuin, Adrià Garriga-Alonso, Mark van der Wilk, Laurence Aitchison

Bayesian neural networks have shown great promise in many applications where calibrated uncertainty estimates are crucial and can often also lead to a higher predictive performance. However, it remains challenging to cho…

Exact marginal prior distributions of finite Bayesian neural networks

2021-04-23 · NeurIPS 2021 12 · Jacob A. Zavatone-Veth, Cengiz Pehlevan

Bayesian neural networks are theoretically well-understood only in the infinite-width limit, where Gaussian priors over network weights yield Gaussian priors over network outputs. Recent work has suggested that finite Ba…