机器学习：贝叶斯和优化方法_Facebook如何使用贝叶斯优化在机器学习模型中进行更好的实验.pdfVIP

机器学习：贝叶斯和优化⽅法_Facebook如何使⽤贝叶斯优化 在机器学习模型中进⾏更好的实验 机器学习:贝叶斯和优化⽅法 重点 (Top highlight) I recently started a new newsletter focus on AI education. TheSequence is a no-BS( meaning no hype, no news etc) AI- focused newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. Please give it a try by subscribing below: 我最近开始了⼀份有关AI教育的新时事通讯。 TheSequence是⽆BS(意味着没有炒作，没有新闻等)，它是专注于AI的新闻通讯，需 要5分钟的阅读时间。 ⽬标是让您了解机器学习项⽬，研究论⽂和概念的最新动态。 请通过以下订阅尝试⼀下： Hyperparameter optimization is a key aspect of the lifecycle of machine learning applications. While methods such as grid search are incredibly effective for optimizing hyperparameters for specific isolated models, they are very difficult to scale across large permutations of models and experiments. A company like Facebook operates thousands of concurrent machine learning models that need to be constantly tuned. To achieve that, Facebook engineering teams need to regularly conduct A/B tests in order to determine the right hyperparameter configuration. Data in those tests is difficult to collect and they are typically conducted in isolation of each other which end up resulting in very computationally expensive exercises. Tools for rapid experimentation and hyper parameter optimization are rapidly emerging in the deep learning but its hard to imagine how to apply it at large scale. From the studies in the market, one of my favorites is a research paper published bya team of AI researchers from Facebook to adaptively design rounds of A/B tests based on the results of prior tests. 超参数优化是机器学习应⽤程序⽣命周期的关键⽅⾯。 尽管诸如⽹格搜索之类的⽅法对于优化特定隔离模型的超参数⾮常有效，但它们很 难在较⼤的模型和实验排列范围内扩展。 像Facebook这样的公司运营着成千上万个需要不断调整的并发机器学习模型。 为此，Facebook ⼯程团队需要定期进⾏A / B测试，以确定正确的超参数配置。 这些测试中的数据很难收集，它们通常彼此隔离地进⾏，最终导致计算量很 ⼤。 ⽤于快速实验和超参数优化的⼯具在深度学习中Swift兴起，但是很难想象如何将其⼤规模应⽤。 从市场上的研究中，我最喜欢的⼀项 研究是由来⾃Facebook的组AI研究⼈员发表的研究论⽂， 先前测试的结果⾃适应地设计A / B测试轮次。 为什么要进⾏贝叶斯优化？ (