Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
A theory of representation learning gives a deep generalisation of kernel methods
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 DKM objective (learned representations) instead of NNGP-style fixed kernel hyperparameters in sparse DGP | sparse DKM · UCI regression (9 datasets, Table 1) | RMSE | Helped |
| Use DKM objective instead of MAP over features | sparse DKM · UCI regression (Table 1) | RMSE | Mixed |
| Wide DGP posterior trained with Langevin vs. infinite-width limit: increasing DGP width toward DKM | finite-width DGP · yacht subset, Gram matrix RMSE | Gram matrix RMSE to DKM | Helped |
| Standard infinite-width limit (NNGP) where likelihood is swamped by prior | DGP infinite width · theoretical | representation learning | Hurt |
| Replicate labels N times (Bayesian representation learning limit) so likelihood scales with width | DGP/DKM objective · theoretical | representation learning | Helped |
Closest papers by meaning
- Convolutional Deep Kernel Machines (ICLR 2024 · similarity 0.93)
- Adaptive kernel predictors from feature-learning infinite limits of neural networks (ICML 2025 · similarity 0.88)
- Critical feature learning in deep neural networks (ICML 2024 · similarity 0.88)
- Deep Kernel Posterior Learning under Infinite Variance Prior Weights (ICLR 2025 · similarity 0.88)
- The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective (NeurIPS 2021 · similarity 0.88)
- An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural Network (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.