Generalization bounds for sparse random feature expansions

Random feature methods have been successful in various machine learning tasks, are easy to compute, and come with theoretical accuracy bounds. They serve as an alternative approach to standard neural networks since they can represent similar function spaces without a costly training phase. However,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied and computational harmonic analysis Jg. 62; S. 310 - 330
Hauptverfasser: Hashemi, Abolfazl, Schaeffer, Hayden, Shi, Robert, Topcu, Ufuk, Tran, Giang, Ward, Rachel
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.01.2023
Schlagworte:
Compressive sensing
Generalization error
Random features
Sparse optimization
Sparse optimization
Compressive sensing
Random features
60B20
Generalization error
65D15
68Q32
46N10
ISSN:1063-5203, 1096-603X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Random feature methods have been successful in various machine learning tasks, are easy to compute, and come with theoretical accuracy bounds. They serve as an alternative approach to standard neural networks since they can represent similar function spaces without a costly training phase. However, for accuracy, random feature methods require more measurements than trainable parameters, limiting their use for data-scarce applications. We introduce the sparse random feature expansion to obtain parsimonious random feature models. We leverage ideas from compressive sensing to generate random feature expansions with theoretical guarantees even in the data-scarce setting. We provide generalization bounds for functions in a certain class depending on the number of samples and the distribution of features. By introducing sparse features, i.e. features with random sparse weights, we provide improved bounds for low order functions. We show that our method outperforms shallow networks in several scientific machine learning tasks.
ISSN:1063-5203
1096-603X
DOI:10.1016/j.acha.2022.08.003