mlsanityData to 14 Oct 2026

From Deep Additive Kernel Learning to Last-Layer Bayesian Neural Networks via Induced Prior Approximation

arXiv 2502.10540 ↗First posted 14 Feb 2025cs.LG stat.MLcited by 2

Not on the map. Why?

Abstract (arXiv)

With the strengths of both deep learning and kernel methods like Gaussian Processes (GPs), Deep Kernel Learning (DKL) has gained considerable attention in recent years. From the computational perspective, however, DKL becomes challenging when the input dimension of the GP layer is high. To address this challenge, we propose the Deep Additive Kernel (DAK) model, which incorporates i) an additive structure for the last-layer GP; and ii) induced prior approximation for each GP unit. This naturally leads to a last-layer Bayesian neural network (BNN) architecture. The proposed method enjoys the interpretability of DKL as well as the computational advantages of BNN. Empirical results show that the proposed approach outperforms state-of-the-art DKL methods in both regression and classification tasks.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 54 references that are in the map. First posted on arXiv 14 Feb 2025.

Builds on

25 of 54 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017Deep Neural Networks as Gaussian Processescited by 622
  4. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 609
  5. 2015Deep Kernel Learningcited by 445
  6. 2018Gaussian Process Behaviour in Wide Deep Neural Networkscited by 317
  7. 2014Scalable Variational Gaussian Process Classificationcited by 228
  8. 2015Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)cited by 177
  9. 2018Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processescited by 167
  10. 2019Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processescited by 151
  11. 2018Deep Convolutional Networks as shallow Gaussian Processescited by 138
  12. 2016Stochastic Variational Deep Kernel Learningcited by 93
13 more
  1. 2021The Promises and Pitfalls of Deep Kernel Learningcited by 81
  2. 2024Variational Bayesian Last Layerscited by 69
  3. 2017Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networkscited by 48
  4. 2016Random Feature Expansions for Deep Gaussian Processescited by 32
  5. 2021Deep Neural Networks as Point Estimates for Deep Gaussian Processescited by 26
  6. 2018Differentiable Compositional Kernel Learning for Gaussian Processescited by 23
  7. 2016Learning Scalable Deep Kernels with Recurrent Structurecited by 22
  8. 2019Randomly Projected Additive Gaussian Processes for Regressioncited by 19
  9. 2023Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Modelscited by 14
  10. 2024Gaussian Process Neural Additive Modelscited by 11
  11. 2019Deep Kernel Learning via Random Fourier Featurescited by 7
  12. 2021Input Dependent Sparse Gaussian Processescited by 5
  13. 2021A Sparse Expansion For Deep Gaussian Processescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Scalable Deep Basis Kernel Gaussian Processescited by 0
  2. 2026SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learningcited by 0