Coresets are small data summaries used for effective model training. They offer a solution for managing large data streams efficiently under resource constraints. This paper aims to investigate some alternative bilevel optimization approaches to determine coresets for deep neural networks and provide empirical evidence of their advantages.
Coresets are small data summaries used for effective model training. They offer a solution for managing large data streams efficiently under resource constraints. This paper aims to investigate some alternative bilevel optimization approaches to determine coresets for deep neural networks and provide empirical evidence of their advantages.
Optimization Approaches for Continual Learning
PERNINI, MATTEO
2023/2024
Abstract
Coresets are small data summaries used for effective model training. They offer a solution for managing large data streams efficiently under resource constraints. This paper aims to investigate some alternative bilevel optimization approaches to determine coresets for deep neural networks and provide empirical evidence of their advantages.| File | Dimensione | Formato | |
|---|---|---|---|
|
Pernini_Matteo.pdf
accesso riservato
Dimensione
1.47 MB
Formato
Adobe PDF
|
1.47 MB | Adobe PDF |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/68385