Learning Multi-Index Models with Hyper-Kernel Ridge Regression
stat.ML, cs.LG
Submitted: 2025-10-02
Updated: 2026-09-08
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Survey on Algorithms for multi-index models
- A Theory of Feature Learning in Kernel Models
- How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
- Enhanced Feature Learning via Regularisation: Integrating Neural Networks and Kernel Methods
- A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
- Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
- Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features
- Linear Recursive Feature Machines provably recover low-rank matrices
- Iteratively reweighted kernel machines efficiently learn sparse functions
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey