#machine learning
Oct 2025
Learning Multi-Index Models with Hyper-Kernel Ridge Regression
This work introduces and studies hyper-kernel ridge regression (HKRR), an approach blending neural networks and kernel methods, and exploits the kernel nature of the estimator to develop ad hoc optimization approaches.
Shuo Huang, Hippolyte Labarrière, E. De Vito et al.
· arXiv.org · 2 citations