How Deep Are Deep Gaussian Processes?

zbMath1469.60107arXiv1711.11280MaRDI QIDQ4558207

A. L. Teckentrup, Matthew M. Dunlop, Mark A. Girolami, Andrew M. Stuart

Publication date: 21 November 2018

Full work available at URL: https://arxiv.org/abs/1711.11280

zbMATH Keywords

deep learningdeep Gaussian processesdeep kernels

Mathematics Subject Classification ID

Gaussian processes (60G15) Artificial neural networks and deep learning (68T07) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20)

Related Items (22)

Cauchy Markov random field priors for Bayesian inversion ⋮ Likelihood-free inference with deep Gaussian processes ⋮ A survey of deep network techniques all classifiers can adopt ⋮ Priors in Bayesian Deep Learning: A Review ⋮ Bayesian inversion with α-stable priors ⋮ Posterior inference for sparse hierarchical non-stationary models ⋮ Nonstationary Gaussian Process Discriminant Analysis With Variable Selection for High-Dimensional Functional Data ⋮ Deep Compositional Spatial Models ⋮ Bayesian Inverse Problems Are Usually Well-Posed ⋮ Foundations of Bayesian inference for complex statistical models. Abstracts from the workshop held May 2--8, 2021 (hybrid meeting) ⋮ Hyperpriors for Matérn fields with applications in Bayesian inversion ⋮ Non-stationary multi-layered Gaussian priors for Bayesian inversion ⋮ Emulating dynamic non-linear simulators using Gaussian processes ⋮ Vecchia-approximated Deep Gaussian Processes for Computer Experiments ⋮ Diagnostics-Driven Nonstationary Emulators Using Kernel Mixtures ⋮ On the Well-posedness of Bayesian Inverse Problems ⋮ Multilevel quasi-Monte Carlo integration with product weights for elliptic PDEs with lognormal coefficients ⋮ Deep state-space Gaussian processes ⋮ Uncertainty quantification of a computer model for binary black hole formation ⋮ Rejoinder: ``Probabilistic integration: a role in statistical computation? ⋮ Unnamed Item ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An Explicit Link between Gaussian Fields and Gaussian Markov Random Fields: The Stochastic Partial Differential Equation Approach
• A Bayesian level set method for geometric inverse problems
• A general framework for the parametrization of hierarchical models
• Whittle-Matérn priors for Bayesian statistical inversion with applications in electrical impedance tomography
• Interpolation of spatial data. Some theory for kriging
• Statistical and computational inverse problems.
• Mitigating the influence of the boundary on PDE-based covariance operators
• Bayesian learning for neural networks
• Analysis of SPDEs arising in path sampling. I: The Gaussian case
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Bayesian Calibration of Computer Models
• Kullback--Leibler Approximation for Probability Measures on Infinite Dimensional Spaces
• Markov Chains and Stochastic Stability
• Iterated Random Functions
• Parameterizations for ensemble Kalman inversion
• Stable architectures for deep neural networks
• Combining Field Data and Computer Simulations for Calibration and Prediction
• Bayesian Inference for Non-Stationary Spatial Covariance Structure via Spatial Deformations
• Scattered Data Approximation
• MCMC methods for functions: modifying old algorithms to make them faster

This page was built for publication: How Deep Are Deep Gaussian Processes?