The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets

NeurIPSSpotlight2025

Authors: Yatin Dandi, Luca Pesce, Lenka Zdeborova, Florent Krzakala
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Understanding the advantages of deep neural networks trained by gradient descent (GD) compared to shallow models remains an open theoretical challenge…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

← All NeurIPS 2025 Spotlight papers · Browse the whole archive