mlsanityData to 14 Oct 2026

GPflux: A Library for Deep Gaussian Processes

arXiv 2104.05674 ↗First posted 12 Apr 2021stat.ML cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

We introduce GPflux, a Python library for Bayesian deep learning with a strong emphasis on deep Gaussian processes (DGPs). Implementing DGPs is a challenging endeavour due to the various mathematical subtleties that arise when dealing with multivariate Gaussian distributions and the complex bookkeeping of indices. To date, there are no actively maintained, open-sourced and extendable libraries available that support research activities in this area. GPflux aims to fill this gap by providing a library with state-of-the-art DGP algorithms, as well as building blocks for implementing novel Bayesian and GP-based hierarchical models and inference schemes. GPflux is compatible with and built on top of the Keras deep learning eco-system. This enables practitioners to leverage tools from the deep learning community for building and training customised Bayesian models, and create hierarchical models that consist of Bayesian and standard neural network layers in a single coherent framework. GPflux relies on GPflow for most of its GP objects and operations, which makes it an efficient, modular and extensible library, while having a lean codebase.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

18 of 25 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  3. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 664
  4. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  5. 2014Scalable Variational Gaussian Process Classificationcited by 228
  6. 2017Doubly Stochastic Variational Inference for Deep Gaussian Processescited by 143
  7. 2016GPflow: A Gaussian process library using TensorFlowcited by 140
  8. 2017TensorFlow Distributionscited by 106
  9. 2020A Framework for Interdomain and Multioutput Gaussian Processescited by 48
  10. 2017Convolutional Gaussian Processescited by 44
  11. 2018Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Modelscited by 38
  12. 2018Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlocited by 32
6 more
  1. 2020A Tutorial on Sparse Gaussian Processes and Variational Inferencecited by 31
  2. 2018Gaussian Process Conditional Density Estimationcited by 23
  3. 2018Deep convolutional Gaussian processescited by 21
  4. 2019Bayesian Image Classification with Deep Convolutional Gaussian Processescited by 21
  5. 2015Variational Auto-encoded Deep Gaussian Processescited by 20
  6. 2019Deep Gaussian Processes with Importance-Weighted Variational Inferencecited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 0; 2023: 3; 2024: 2; 2025: 1; 2026: 2.

13 papers.

Sort:

  1. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  2. 2021Deep Neural Networks as Point Estimates for Deep Gaussian Processescited by 26
  3. 2021The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspectivecited by 21
  4. 2021Deep Gaussian Process Emulation using Stochastic Imputationcited by 11
  5. 2023Trieste: Efficiently Exploring The Depths of Black-box Functions with TensorFlowcited by 11
  6. 2023A Unifying Perspective on Non-Stationary Kernels for Deeper Gaussian Processescited by 8
  7. 2024Deep Horseshoe Gaussian Processescited by 5
  8. 2023Thin and Deep Gaussian Processescited by 3
  9. 2021Conditional Deep Gaussian Processes: empirical Bayes hyperdata learningcited by 1
  10. 2024Gearing Gaussian process modeling and sequential design towards stochastic simulatorscited by 1
  11. 2025Tracking Wildfire Assets with Commodity RFID and Gaussian Process Modelingcited by 1
  12. 2026Inverse-Free Sparse Variational Gaussian Processescited by 0
1 more
  1. 2026An Analysis of Posterior Collapse, Parameterization and Initialization in Variational Deep Gaussian Processescited by 0