Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Approximate Inference Turns Deep Networks into Gaussian 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 the GP marginal likelihood on training data to tune DNN hyperparameters | DNN2GP-Laplace · UCI Red Wine Quality | test error | Helped |
| Use the GP marginal likelihood on training data to tune the regularization parameter | DNN2GP · Synthetic regression dataset | test MSE | Helped |
| Tune regularization by reducing δ using training MSE | DNN · Synthetic regression dataset | test MSE | Hurt |
| Use DNN2GP predictive uncertainty rather than the compared methods' uncertainty | DNN2GP-Laplace and DNN2GP-VI · Modified Snelson dataset | predictive uncertainty in unobserved regions | Helped |
Closest papers by meaning
- Deep Gaussian Processes for Regression using Approximate Expectation Propagation (ICML 2016 · similarity 0.91)
- Deep Neural Networks as Gaussian Processes (ICLR 2018 · similarity 0.91)
- SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning (ICML 2026 · similarity 0.89)
- Gaussian Process Behaviour in Wide Deep Neural Networks (ICLR 2018 · similarity 0.89)
- Doubly Stochastic Variational Inference for Deep Gaussian Processes (NeurIPS 2017 · similarity 0.89)
- Random Feature Expansions for Deep Gaussian Processes (ICML 2017 · similarity 0.88)
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.