Survey on Algorithms for Multi-Index Models
Statistical Science · 01.08.2025 · 40 (3) · 378-391
DOI: 10.1214/25-sts993 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistical Science, erschienen am 01.08.2025. Verfasst von Joan Bruna und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 93 Literaturangaben.
Abstract (Originalsprache)
We review the literature on algorithms for estimating the index space in a multi-index model. The primary focus is on computationally efficient (polynomial-time) algorithms in Gaussian space, the assumptions under which consistency is guaranteed by these methods, and their sample complexities. In many cases, a gap is observed between the sample complexity of the best known computationally efficient methods and the information-theoretical minimum. We also review algorithms based on estimating the span of gradients using nonparametric methods, and algorithms based on fitting neural networks using gradient descent.
Zitieren
APA
Bruna, J., & Hsu, D. (2025). Survey on Algorithms for Multi-Index Models. Statistical Science, 40(3), 378-391. https://doi.org/10.1214/25-sts993
Vancouver
Bruna J, Hsu D. Survey on Algorithms for Multi-Index Models. Statistical Science. 2025;40(3):378-391. doi:10.1214/25-sts993
BibTeX
@article{Bruna2025,
author = {Bruna, Joan and Hsu, Daniel},
title = {Survey on Algorithms for Multi-Index Models},
journal = {Statistical Science},
year = {2025},
volume = {40},
number = {3},
pages = {378--391},
doi = {10.1214/25-sts993}
}
EUVIMED