Scheduling Machine Learning Compressible Inference Tasks with Limited Energy Budget

Author:

Da Silva Barros Tiago1ORCID,Ferre Davide2ORCID,Giroire Frederic3ORCID,Aparicio-Pardo Ramon4ORCID,Perennes Stephane2ORCID

Affiliation:

1. Université Côte d'Azur, Inria, I3S, France

2. Inria, France

3. CNRS, France

4. Université Côte d'Azur, CNRS, I3S, France

Funder

Agence Nationale de la Recherche

European Network of Excellence dAIEDGE

Publisher

ACM

Reference29 articles.

1. MOSEK ApS. 2022. The MOSEK optimization toolbox for Python manual. Version 10.0.https://docs.mosek.com/latest/pythonapi/index.html

2. Stephen P Boyd and Lieven Vandenberghe. 2004. Convex optimization. Cambridge university press.

3. Han Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, and Song Han. 2020. Once-for-All: Train One Network and Specialize it for Efficient Deployment. In International Conference on Learning Representations.

4. Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and Challenges

5. Tiago Da Silva Barros, Frederic Giroire, Ramon Aparicio-Pardo, Stephane Perennes, and Emanuele Natale. 2024. Scheduling with Fully Compressible Tasks: Application to Deep Learning Inference with Neural Network Compression. In IEEE/ACM International Symposium on Cluster, Cloud, and Internet Computing.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3