arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.04728cs.LG
收藏

PyHopper --超参数优化

PyHopper -- Hyperparameter optimization

Massachusetts Institute of Technology(麻省理工学院);Simple AI;DatenVorspung GmbH(DatenVorspung有限公司)

Mathias Lechner, Ramin Hasani, Philipp Neubauer, Sophie Neubauer, Daniela Rus

摘要:

超参数整定是机器学习研究的一个基本方面。建立用于系统优化超参数的基础设施可能需要大量时间。在这里,我们介绍了PyHopper,一个黑盒优化平台,旨在简化机器学习研究人员的超参数调整工作流程。PyHopper的目标是以最小的努力与现有代码集成,并以最少的必要手动监督运行优化过程。以简单为主题,PyHopper由一个强大的马尔可夫链蒙特卡罗优化算法提供支持,该算法可扩展到数百万个维度。与现有的调优包相比,专注于单个算法使用户不必在几个算法之间做出决定,并使PyHopper易于定制。PyHopper在Apache-2.0许可证下可在https://github.com/PyHopper/PyHopper上公开获得。

英文摘要:

Hyperparameter tuning is a fundamental aspect of machine learning research. Setting up the infrastructure for systematic optimization of hyperparameters can take a significant amount of time. Here, we present PyHopper, a black-box optimization platform designed to streamline the hyperparameter tuning workflow of machine learning researchers. PyHopper's goal is to integrate with existing code with minimal effort and run the optimization process with minimal necessary manual oversight. With simplicity as the primary theme, PyHopper is powered by a single robust Markov-chain Monte-Carlo optimization algorithm that scales to millions of dimensions. Compared to existing tuning packages, focusing on a single algorithm frees the user from having to decide between several algorithms and makes PyHopper easily customizable. PyHopper is publicly available under the Apache-2.0 license at https://github.com/PyHopper/PyHopper.

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。

↑