GreenAuto: An Automated Platform for Sustainable AI Model Design on Edge Devices
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929686545694720 |
|---|---|
| author | Tu, Xiaolong Chen, Dawei Han, Kyungtae Altintas, Onur Wang, Haoxin |
| author_facet | Tu, Xiaolong Chen, Dawei Han, Kyungtae Altintas, Onur Wang, Haoxin |
| contents | We present GreenAuto, an end-to-end automated platform designed for sustainable AI model exploration, generation, deployment, and evaluation. GreenAuto employs a Pareto front-based search method within an expanded neural architecture search (NAS) space, guided by gradient descent to optimize model exploration. Pre-trained kernel-level energy predictors estimate energy consumption across all models, providing a global view that directs the search toward more sustainable solutions. By automating performance measurements and iteratively refining the search process, GreenAuto demonstrates the efficient identification of sustainable AI models without the need for human intervention. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14995 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GreenAuto: An Automated Platform for Sustainable AI Model Design on Edge Devices Tu, Xiaolong Chen, Dawei Han, Kyungtae Altintas, Onur Wang, Haoxin Machine Learning We present GreenAuto, an end-to-end automated platform designed for sustainable AI model exploration, generation, deployment, and evaluation. GreenAuto employs a Pareto front-based search method within an expanded neural architecture search (NAS) space, guided by gradient descent to optimize model exploration. Pre-trained kernel-level energy predictors estimate energy consumption across all models, providing a global view that directs the search toward more sustainable solutions. By automating performance measurements and iteratively refining the search process, GreenAuto demonstrates the efficient identification of sustainable AI models without the need for human intervention. |
| title | GreenAuto: An Automated Platform for Sustainable AI Model Design on Edge Devices |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.14995 |