Summary of Carbon-efficient Neural Architecture Search, by Yiyang Zhao and Tian Guo
Carbon-Efficient Neural Architecture Search
by Yiyang Zhao, Tian Guo
First submitted to arxiv on: 9 Jul 2023
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to neural architecture search (NAS) that reduces energy costs and increases carbon efficiency during model design. The carbon-efficient NAS (CE-NAS) framework combines NAS evaluation algorithms with different energy requirements, a multi-objective optimizer, and a heuristic GPU allocation strategy. CE-NAS dynamically balances energy-efficient sampling and energy-consuming evaluation tasks based on current carbon emissions. Using recent NAS benchmark datasets and carbon traces, the simulations demonstrate that CE-NAS outperforms three baselines in terms of both carbon and search efficiency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding ways to make it more efficient and environmentally friendly to design new models for artificial intelligence. Right now, designing these models uses a lot of energy, which can hurt the environment. The scientists came up with a new way to do this called CE-NAS (carbon-efficient neural architecture search). It does this by balancing how much energy is used during the design process and finding ways to make it more efficient. |
