High-dimensional learning dynamics of multi-pass Stochastic Gradient Descent in multi-index models

arXiv:2601.21093v2 Announce Type: replace-cross Abstract: We study the learning dynamics of a multi-pass, mini-batch Stochastic Gradient Descent (SGD) procedure for empirical risk minimization in high-dimensional multi-index models with isotropic random data. In an asymptotic ...

🔗 Read more: https://arxiv.org/abs/2601.21093

#News #Software #Energy #Math #Policy #Academic