Details
Originalsprache | Englisch |
---|---|
Titel des Sammelwerks | 5th Workshop on practical ML for limited/low resource settings |
Publikationsstatus | Elektronisch veröffentlicht (E-Pub) - 2 Apr. 2024 |
Abstract
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
5th Workshop on practical ML for limited/low resource settings. 2024.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Towards Leveraging AutoML for Sustainable Deep Learning
T2 - A Multi-Objective HPO Approach on Deep Shift Neural Networks
AU - Hennig, Leona
AU - Tornede, Tanja
AU - Lindauer, Marius
PY - 2024/4/2
Y1 - 2024/4/2
N2 - Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep shift neural networks (DSNNs) offer a solution by leveraging shift operations to reduce computational complexity at inference. Following the insights from standard DNNs, we are interested in leveraging the full potential of DSNNs by means of AutoML techniques. We study the impact of hyperparameter optimization (HPO) to maximize DSNN performance while minimizing resource consumption. Since this combines multi-objective (MO) optimization with accuracy and energy consumption as potentially complementary objectives, we propose to combine state-of-the-art multi-fidelity (MF) HPO with multi-objective optimization. Experimental results demonstrate the effectiveness of our approach, resulting in models with over 80\% in accuracy and low computational cost. Overall, our method accelerates efficient model development while enabling sustainable AI applications.
AB - Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep shift neural networks (DSNNs) offer a solution by leveraging shift operations to reduce computational complexity at inference. Following the insights from standard DNNs, we are interested in leveraging the full potential of DSNNs by means of AutoML techniques. We study the impact of hyperparameter optimization (HPO) to maximize DSNN performance while minimizing resource consumption. Since this combines multi-objective (MO) optimization with accuracy and energy consumption as potentially complementary objectives, we propose to combine state-of-the-art multi-fidelity (MF) HPO with multi-objective optimization. Experimental results demonstrate the effectiveness of our approach, resulting in models with over 80\% in accuracy and low computational cost. Overall, our method accelerates efficient model development while enabling sustainable AI applications.
KW - cs.LG
KW - cs.AI
U2 - https://doi.org/10.48550/arXiv.2404.01965
DO - https://doi.org/10.48550/arXiv.2404.01965
M3 - Conference contribution
BT - 5th Workshop on practical ML for limited/low resource settings
ER -