Rademacher learning rates for iterated random functions

Most supervised learning methods assume training data is drawn from an i.i.d. sample. However, real-world problems often exhibit temporal dependence and strong correlations between marginals of the data-generating process, rendering the i.i.d. assumption unrealistic. Such cases naturally involve tim...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of Complexity Jg. 91; S. 101971
1. Verfasser:	Sandrić, Nikola
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Inc 01.12.2025
Schlagworte:	Approximate empirical risk minimization algorithm Iterated random function Rademacher complexity Wasserstein distance Approximate empirical risk minimization algorithm 68W40 68T10 Rademacher complexity Wasserstein distance 60J05 Iterated random function
ISSN:	0885-064X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!