PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search

The wide application of pre-trained models is driving the trend of once-for-all training in one-shot neural architecture search (NAS). However, training within a huge sample space damages the performance of individual subnets and requires much computation to search for an optimal model. In this pape...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-06
Hauptverfasser:	Wang, Haibin, Ge, Ce, Chen, Hesen, Sun, Xiuyu
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer networks Searching Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!