Research map / Learning theory and algorithms / Kernels and regression theory
Learning Infinite Layer Networks Without the Kernel Trick
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 Shrinking Gradient instead of the compared random-feature methods at the same overall feature budget | Random-feature regression · Synthetic high-dimensional regression | loss | Helped |
| Replace exact kernel values with sampled, unbiased scalar-product estimates | Online learning of infinite-layer networks · Online squared-loss regression | regret: O(B\sqrt{T}) | Helped |
Closest papers by meaning
- Finite Versus Infinite Neural Networks: an Empirical Study (NeurIPS 2020 · similarity 0.87)
- L1-regularized Neural Networks are Improperly Learnable in Polynomial Time (ICML 2016 · similarity 0.86)
- An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural Network (ICML 2024 · similarity 0.84)
- Just One Layer Norm Guarantees Stable Extrapolation (NeurIPS 2025 · similarity 0.84)
- Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\mu$ Parametrization (ICML 2025 · similarity 0.83)
- Adaptive kernel predictors from feature-learning infinite limits of neural networks (ICML 2025 · similarity 0.83)
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.