Research map / Learning theory and algorithms / Kernels and regression theory
Deterministic equivalent and error universality of deep random features learning
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 |
|---|---|---|---|
| Replace deep random features with a Gaussian covariate model matched on second moments | Deep random features learning with generic architectures and convex loss · Generic target/learner architectures | test error | No clear effect |
| Increase depth with tanh activations | Deep random features learner · Ridge regression learning curves | test error at the linear peak | Hurt |
| Increase depth with tanh activations | Deep random features learner · Ridge regression learning curves | test error at the nonlinear peak | Helped |
| Increase depth with clipped linear activations | Deep random features learner · Ridge regression learning curves | test error at the linear peak | Helped |
| Increase depth with clipped linear activations | Deep random features learner · Ridge regression learning curves | test error at the nonlinear peak | Hurt |
Closest papers by meaning
- Asymptotics of Learning with Deep Structured (Random) Features (ICML 2024 · similarity 0.89)
- Asymptotics of feature learning in two-layer networks after one gradient-step (ICML 2024 · similarity 0.86)
- Universality in Transfer Learning for Linear Models (NeurIPS 2024 · similarity 0.86)
- Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method (NeurIPS 2026 · similarity 0.86)
- Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure (ICLR 2025 · similarity 0.85)
- Dimension-free deterministic equivalents and scaling laws for random feature regression (NeurIPS 2024 · similarity 0.85)
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.