Can I read On Learning Gaussian Multi-index Models with Gradient Flow on EtoBox?

On Learning Gaussian Multi-index Models with Gradient Flow by Bietti, Alberto; Bruna, Joan; Pillaud-Vivien, Loucas is a scholarly article available to read on EtoBox.

What is On Learning Gaussian Multi-index Models with Gradient Flow about?

We study gradient flow on the multi-index regression problem for high-dimensional Gaussian data. Multi-index functions consist of a composition of an unknown low-rank linear projection and an arbitrary unknown, low-dimensional link function. As such, they constitute a natural template for feature learning in neural networks. We consider a two-timescale algorithm, whereby the low-dimensional link function is learnt with a non-parametric model infinitely faster than the subspace parametrizing the low-rank projection. By appropriately exploiting the matrix semigroup structure arising over the subspace correlation matrices, we establish global convergence of the resulting Grassmannian population gradient flow dynamics, and provide a quantitative description of its associated `saddle-to-saddle' dynamics. Notably, the timescales associated with each saddle can be explicitly characterized in terms of an appropriate Hermite decomposition of the target link function. In contrast with these positive results, we also show that the related \emph{planted} problem, where the link function is known and fixed, in fact has a rough optimization landscape, in which gradient flow dynamics might get tr

Author

Bietti, Alberto; Bruna, Joan; Pillaud-Vivien, Loucas

Published

2023

Language

EN