Saved in:
Bibliographic Details
Main Authors: Huang, Shuo, Labarrière, Hippolyte, De Vito, Ernesto, Poggio, Tomaso, Rosasco, Lorenzo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.02532
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908574261706752
author Huang, Shuo
Labarrière, Hippolyte
De Vito, Ernesto
Poggio, Tomaso
Rosasco, Lorenzo
author_facet Huang, Shuo
Labarrière, Hippolyte
De Vito, Ernesto
Poggio, Tomaso
Rosasco, Lorenzo
contents Deep neural networks excel in high-dimensional problems, outperforming models such as kernel methods, which suffer from the curse of dimensionality. However, the theoretical foundations of this success remain poorly understood. We follow the idea that the compositional structure of the learning task is the key factor determining when deep networks outperform other approaches. Taking a step towards formalizing this idea, we consider a simple compositional model, namely the multi-index model (MIM). In this context, we introduce and study hyper-kernel ridge regression (HKRR), an approach blending neural networks and kernel methods. Our main contribution is a sample complexity result demonstrating that HKRR can adaptively learn MIM, overcoming the curse of dimensionality. Further, we exploit the kernel nature of the estimator to develop ad hoc optimization approaches. Indeed, we contrast alternating minimization and alternating gradient methods both theoretically and numerically. These numerical results complement and reinforce our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02532
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Multi-Index Models with Hyper-Kernel Ridge Regression
Huang, Shuo
Labarrière, Hippolyte
De Vito, Ernesto
Poggio, Tomaso
Rosasco, Lorenzo
Machine Learning
Deep neural networks excel in high-dimensional problems, outperforming models such as kernel methods, which suffer from the curse of dimensionality. However, the theoretical foundations of this success remain poorly understood. We follow the idea that the compositional structure of the learning task is the key factor determining when deep networks outperform other approaches. Taking a step towards formalizing this idea, we consider a simple compositional model, namely the multi-index model (MIM). In this context, we introduce and study hyper-kernel ridge regression (HKRR), an approach blending neural networks and kernel methods. Our main contribution is a sample complexity result demonstrating that HKRR can adaptively learn MIM, overcoming the curse of dimensionality. Further, we exploit the kernel nature of the estimator to develop ad hoc optimization approaches. Indeed, we contrast alternating minimization and alternating gradient methods both theoretically and numerically. These numerical results complement and reinforce our theoretical findings.
title Learning Multi-Index Models with Hyper-Kernel Ridge Regression
topic Machine Learning
url https://arxiv.org/abs/2510.02532