arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.05149cs.LGcs.AIcs.GL
收藏

机器学习培训的碳足迹将趋于稳定,然后缩小

The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink

Google(谷歌);University of California, Berkeley(加州大学伯克利分校)

David Patterson, Joseph Gonzalez, Urs Hölzle, Quoc Le, Chen Liang, Lluis-Miquel Munguia, Daniel Rothchild, David So, Maud Texier, Jeff Dean

摘要:

机器学习(ML)工作负载的重要性迅速增长,但也引发了人们对其碳足迹的担忧。四种最佳实践可以将机器学习培训能源减少高达100倍,二氧化碳排放量减少高达1000倍。通过遵循最佳实践,在过去三年中,总体ML能源使用(包括研究、开发和生产)稳定在Google总能源使用的15%以下。如果整个ML领域都采用最佳实践,那么来自培训的总碳排放量将减少。因此,我们建议ML论文明确包括排放,以促进不仅仅是模型质量的竞争。论文中省略了排放量的估计值已经偏离了100 - 100,000倍,因此公布排放量有确保准确核算的额外好处。考虑到气候变化的重要性,我们必须掌握正确的数字,以确保我们应对其最大的挑战。

英文摘要:

Machine Learning (ML) workloads have rapidly grown in importance, but raised concerns about their carbon footprint. Four best practices can reduce ML training energy by up to 100x and CO2 emissions up to 1000x. By following best practices, overall ML energy use (across research, development, and production) held steady at <15% of Google's total energy use for the past three years. If the whole ML field were to adopt best practices, total carbon emissions from training would reduce. Hence, we recommend that ML papers include emissions explicitly to foster competition on more than just model quality. Estimates of emissions in papers that omitted them have been off 100x-100,000x, so publishing emissions has the added benefit of ensuring accurate accounting. Given the importance of climate change, we must get the numbers right to make certain that we work on its biggest challenges.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑