Local EGOP for Continuous Index Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kokot, Alex, Hemmady, Anand, Thiyageswaran, Vydhourie, Meila, Marina
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915783637991424
author Kokot, Alex
Hemmady, Anand
Thiyageswaran, Vydhourie
Meila, Marina
author_facet Kokot, Alex
Hemmady, Anand
Thiyageswaran, Vydhourie
Meila, Marina
contents We introduce the setting of continuous index learning, in which a function of many variables varies only along a small number of directions at each point. For efficient estimation, it is beneficial for a learning algorithm to adapt, near each point $x$, to the subspace that captures the local variability of the function $f$. We pose this task as kernel adaptation along a manifold with noise, and introduce Local EGOP learning, a recursive algorithm that utilizes the Expected Gradient Outer Product (EGOP) quadratic form as both a metric and inverse-covariance of our target distribution. We prove that Local EGOP learning adapts to the regularity of the function of interest, showing that under a supervised noisy manifold hypothesis, intrinsic dimensional learning rates are achieved for arbitrarily high-dimensional noise. Empirically, we compare our algorithm to the feature learning capabilities of deep learning. Additionally, we demonstrate improved regression quality compared to two-layer neural networks in the continuous single-index setting.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07061
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Local EGOP for Continuous Index Learning
Kokot, Alex
Hemmady, Anand
Thiyageswaran, Vydhourie
Meila, Marina
Machine Learning
We introduce the setting of continuous index learning, in which a function of many variables varies only along a small number of directions at each point. For efficient estimation, it is beneficial for a learning algorithm to adapt, near each point $x$, to the subspace that captures the local variability of the function $f$. We pose this task as kernel adaptation along a manifold with noise, and introduce Local EGOP learning, a recursive algorithm that utilizes the Expected Gradient Outer Product (EGOP) quadratic form as both a metric and inverse-covariance of our target distribution. We prove that Local EGOP learning adapts to the regularity of the function of interest, showing that under a supervised noisy manifold hypothesis, intrinsic dimensional learning rates are achieved for arbitrarily high-dimensional noise. Empirically, we compare our algorithm to the feature learning capabilities of deep learning. Additionally, we demonstrate improved regression quality compared to two-layer neural networks in the continuous single-index setting.
title Local EGOP for Continuous Index Learning
topic Machine Learning
url https://arxiv.org/abs/2601.07061