Overparameterized ReLU Neural Networks Learn the Simplest Model: Neural Isometry and Phase Transitions
IEEE Transactions on Information Theory · 2025-03 · 71 (3) · 1926-1977
DOI: 10.1109/tit.2025.3530355 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Information Theory, 2025-03. Verfasst von Yifei Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Science Foundation (NSF) CAREER Award, U.S. Army Research Office Early Career Award, Office of Naval Research.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- National Science Foundation (NSF) CAREER Award
- U.S. Army Research Office Early Career Award
- Office of Naval Research
- National Science Foundation
- Simons Foundation
- NSF CAREER Award
Zitieren
APA
Wang, Y., Hua, Y., Candès, E. J., & Pilanci, M. (2025). Overparameterized ReLU Neural Networks Learn the Simplest Model: Neural Isometry and Phase Transitions. IEEE Transactions on Information Theory, 71(3), 1926-1977. https://doi.org/10.1109/tit.2025.3530355
Vancouver
Wang Y, Hua Y, Candès EJ, Pilanci M. Overparameterized ReLU Neural Networks Learn the Simplest Model: Neural Isometry and Phase Transitions. IEEE Transactions on Information Theory. 2025;71(3):1926-1977. doi:10.1109/tit.2025.3530355
BibTeX
@article{Wang2025,
author = {Wang, Yifei and Hua, Yixuan and Candès, Emmanuel J. and Pilanci, Mert},
title = {Overparameterized ReLU Neural Networks Learn the Simplest Model: Neural Isometry and Phase Transitions},
journal = {IEEE Transactions on Information Theory},
year = {2025},
volume = {71},
number = {3},
pages = {1926--1977},
doi = {10.1109/tit.2025.3530355}
}
EUVIMED