Tu(r)ning AI Green: Exploring Energy Efficiency Cascading with Orthogonal Optimizations
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908416775028736 |
|---|---|
| author | Rajput, Saurabhsingh Saad, Mootez Sharma, Tushar |
| author_facet | Rajput, Saurabhsingh Saad, Mootez Sharma, Tushar |
| contents | AI's exponential growth intensifies computational demands and energy challenges. While practitioners employ various optimization techniques, that we refer as "knobs" in this paper, to tune model efficiency, these are typically afterthoughts and reactive ad-hoc changes applied in isolation without understanding their combinatorial effects on energy efficiency. This paper emphasizes on treating energy efficiency as the first-class citizen and as a fundamental design consideration for a compute-intensive pipeline. We show that strategic selection across five AI pipeline phases (data, model, training, system, inference) creates cascading efficiency. Experimental validation shows orthogonal combinations reduce energy consumption by up to $94.6$% while preserving $95.95$% of the original F1 score of non-optimized pipelines. This curated approach provides actionable frameworks for informed sustainable AI that balance efficiency, performance, and environmental responsibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18289 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tu(r)ning AI Green: Exploring Energy Efficiency Cascading with Orthogonal Optimizations Rajput, Saurabhsingh Saad, Mootez Sharma, Tushar Software Engineering Artificial Intelligence AI's exponential growth intensifies computational demands and energy challenges. While practitioners employ various optimization techniques, that we refer as "knobs" in this paper, to tune model efficiency, these are typically afterthoughts and reactive ad-hoc changes applied in isolation without understanding their combinatorial effects on energy efficiency. This paper emphasizes on treating energy efficiency as the first-class citizen and as a fundamental design consideration for a compute-intensive pipeline. We show that strategic selection across five AI pipeline phases (data, model, training, system, inference) creates cascading efficiency. Experimental validation shows orthogonal combinations reduce energy consumption by up to $94.6$% while preserving $95.95$% of the original F1 score of non-optimized pipelines. This curated approach provides actionable frameworks for informed sustainable AI that balance efficiency, performance, and environmental responsibility. |
| title | Tu(r)ning AI Green: Exploring Energy Efficiency Cascading with Orthogonal Optimizations |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2506.18289 |