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 1803.09820cs.LGcs.CVcs.NEstat.ML
收藏

神经网络超参数的规范方法:第1部分--学习率、批量大小、动量和权重衰减

A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay

US Naval Research Laboratory(美国海军研究实验室)

Leslie N. Smith

摘要:

尽管在过去几年中,深度学习在图像、语音和视频处理应用方面取得了令人眼花缭乱的成功,但大多数训练都使用了次优的超参数,需要不必要的长训练时间。设置超参数仍然是一种需要多年经验才能获得的黑艺术。本报告提出了几种有效的方法来设置超参数,从而显著减少训练时间并提高性能。具体而言,此报告显示了如何检查训练验证/测试损失函数,以获得欠拟合和过拟合的细微线索,并建议了向最佳平衡点移动的指导原则。然后讨论了如何提高/降低学习率/动量以加快训练速度。我们的实验表明,平衡每个数据集和架构的各种正则化方式至关重要。权重衰减被用作样本正则化器,以显示其最佳值如何与学习率和动量紧密耦合。可获得帮助复制此处报告的结果的文件。

英文摘要:

Although deep learning has produced dazzling successes for applications of image, speech, and video processing in the past few years, most trainings are with suboptimal hyper-parameters, requiring unnecessarily long training times. Setting the hyper-parameters remains a black art that requires years of experience to acquire. This report proposes several efficient ways to set the hyper-parameters that significantly reduce training time and improves performance. Specifically, this report shows how to examine the training validation/test loss function for subtle clues of underfitting and overfitting and suggests guidelines for moving toward the optimal balance point. Then it discusses how to increase/decrease the learning rate/momentum to speed up training. Our experiments show that it is crucial to balance every manner of regularization for each dataset and architecture. Weight decay is used as a sample regularizer to show how its optimal value is tightly coupled with the learning rates and momentums. Files to help replicate the results reported here are available.

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。

↑