Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Deep kernel processes
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DIWP instead of DGP or NNGP | fully connected models · UCI benchmarks, ReLU and squared exponential kernels | predictive log-likelihood | Helped |
| Use DIWP instead of DGP or NNGP | fully connected models · MNIST | test accuracy: 96.5 ± 0.0% -> 97.7± 0.0% | Helped |
| Use DIWP instead of DGP or NNGP | fully connected models · CIFAR-10 | test accuracy: 47.4 ± 0.1% -> 50.5± 0.1% | Helped |
| Use DIWP instead of DGP or NNGP | fully connected models · MNIST | test log-likelihood: -0.134 ± 0.002 -> -0.089± 0.001 | Helped |
| Use DIWP instead of DGP or NNGP | fully connected models · CIFAR-10 | test log-likelihood: -1.539 ± 0.002 -> -1.433± 0.004 | Helped |
| Increase inverse-Wishart degrees of freedom toward the infinite-width limit | DIWP · general | representation flexibility | Hurt |
Closest papers by meaning
- A variational approximate posterior for the deep Wishart process (NeurIPS 2021 · similarity 0.95)
- Stochastic Variational Deep Kernel Learning (NeurIPS 2016 · similarity 0.88)
- SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning (ICML 2026 · similarity 0.88)
- Convolutional Deep Kernel Machines (ICLR 2024 · similarity 0.88)
- Deep Kernel Posterior Learning under Infinite Variance Prior Weights (ICLR 2025 · similarity 0.86)
- Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.