Symmetry-Aware Feature Learning: A Polynomial Separation for Multi-Index Models

2026-10-07来源 arXiv stat.MLEnglish
arXiv:2610.08420v1 Announce Type: cross Abstract: We establish a polynomial sample complexity separation between symmetry-aware and symmetry-agnostic feature learning. We study growing-rank multi-index models with high-dimensional Gaussian covariates in $\mathbb{R}^d$ and $r=\Theta(d^\delta)$ teacher directions forming a cyclic symmetry orbit, where $0

原文：https://www.a8q9.cn/en/article/symmetry-aware-feature-learning-a-polynomial-separation-for-multi-index-models-9a3230.html

相关文章