mlsanityData to 7 Oct 2026

Convolutional Gaussian Processes

arXiv 1709.01894 ↗First posted 6 Sep 2017stat.ML cs.LGcited by 44

Not on the map. Why?

Abstract (arXiv)

We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images. The main contribution of our work is the construction of an inter-domain inducing point approximation that is well-tailored to the convolutional kernel. This allows us to gain the generalisation benefit of a convolutional kernel, together with fast but accurate posterior inference. We investigate several variations of the convolutional kernel, and apply it to MNIST and CIFAR-10, which have both been known to be challenging for Gaussian processes. We also show how the marginal likelihood can be used to find an optimal weighting between convolutional and RBF kernels to further improve performance. We hope that this illustration of the usefulness of a marginal likelihood will help automate discovering architectures in larger models.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 14; 2023: 7; 2024: 4; 2025: 3; 2026: 3.

44 papers.

Sort:

  1. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  2. 2021The Promises and Pitfalls of Deep Kernel Learningcited by 81
  3. 2021Pre-trained Gaussian Processes for Bayesian Optimizationcited by 63
  4. 2021Deep Neural Networks as Point Estimates for Deep Gaussian Processescited by 26
  5. 2022Sample-Then-Optimize Batch Neural Thompson Samplingcited by 25
  6. 2022Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learningcited by 20
  7. 2022Combining Multi-Fidelity Modelling and Asynchronous Batch Bayesian Optimizationcited by 16
  8. 2021Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structurecited by 15
  9. 2023A spectrum of physics-informed Gaussian processes for regression in engineeringcited by 13
  10. 2021GPflux: A Library for Deep Gaussian Processescited by 12
  11. 2022Globally Gated Deep Linear Networkscited by 12
  12. 2021Scalable Variational Gaussian Processes via Harmonic Kernel Decompositioncited by 8
32 more
  1. 2022Efficient Transformed Gaussian Processes for Non-Stationary Dependent Multi-class Classificationcited by 7
  2. 2021Transferring model structure in Bayesian transfer learning for Gaussian process regressioncited by 5
  3. 2022Learning Interacting Dynamical Systems with Latent Gaussian Process ODEscited by 5
  4. 2022Revisiting Active Sets for Gaussian Process Decoderscited by 5
  5. 2022Sparse Gaussian Process Hyperparameters: Optimize or Integrate?cited by 4
  6. 2023Actually Sparse Variational Gaussian Processescited by 4
  7. 2024Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equationscited by 4
  8. 2021Correlated Weights in Infinite Limits of Deep Convolutional Neural Networkscited by 3
  9. 2022Quasi-Bayesian Nonparametric Density Estimation via Autoregressive Predictive Updatescited by 3
  10. 2023Convolutional Deep Kernel Machinescited by 3
  11. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  12. 2024Regularized Multi-output Gaussian Convolution Process with Domain Adaptationcited by 3
  13. 2025Tighter sparse variational Gaussian processescited by 3
  14. 2025The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learningcited by 3
  15. 2021Convolutional Normalizing Flows for Deep Gaussian Processescited by 2
  16. 2022Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGANcited by 2
  17. 2022Incorporating Prior Knowledge into Neural Networks through an Implicit Composite Kernelcited by 2
  18. 2023Physics-enhanced Gaussian Process Variational Autoencodercited by 2
  19. 2023Hybrid Modeling Design Patternscited by 2
  20. 2021Evolving-Graph Gaussian Processescited by 1
  21. 2021Modular Gaussian Processes for Transfer Learningcited by 1
  22. 2021Geometry-Aware Hierarchical Bayesian Learning on Manifoldscited by 1
  23. 2022Distributional Gaussian Processes Layers for Out-of-Distribution Detectioncited by 1
  24. 2023Gaussian process deconvolutioncited by 1
  25. 2023Beyond Intuition, a Framework for Applying GPs to Real-World Datacited by 1
  26. 2025Flow-Induced Diagonal Gaussian Processescited by 1
  27. 2022Integrated Gradient attribution for Gaussian Processes with non-Gaussian likelihoodscited by 0
  28. 2022Modeling Disagreement in Automatic Data Labelling for Semi-Supervised Learning in Clinical Natural Language Processingcited by 0
  29. 2024Gaussian Process Model with Tensorial Inputs and Its Application to the Design of 3D Printed Antennascited by 0
  30. 2026Inverse-Free Sparse Variational Gaussian Processescited by 0
  31. 2026Scalable Gaussian process inference via neural feature mapscited by 0
  32. 2026Additive Nonparametric Regression with Spatial and Network Objectscited by 0