Asymptotics of feature learning in two-layer networks after one gradient-step

Hugo Cui; Luca Pesce; Yatin Dandi; Florent Krzakala; Yue Lu; Lenka Zdeborová; Bruno Loureiro

2024 ICML ICML 2024

Asymptotics of feature learning in two-layer networks after one gradient-step

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Hugo Cui, Luca Pesce, Yatin Dandi, Florent Krzakala, Yue Lu, Lenka Zdeborová, Bruno Loureiro

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Architectures > Neural Networks

Keywords

generalization error nonlinear function two-layer network high-dimensional limit gradient descent step spiked random features model

Download PDF