arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.09783cs.LG
收藏

基于Lipschitz老虎机的深度神经网络学习率优化

Learning Rate Optimization for Deep Neural Networks Using Lipschitz Bandits

Indian Institute of Technology Madras(印度马德拉斯理工学院)

Padma Priyanka, Sheetal Kalyani, Avhishek Chatterjee

AI总结:

针对神经网络学习率调优问题,提出Lipschitz老虎机驱动的优化方法,相比HyperOpt与BLiE可通过更少评估次数和单评估轮数找到更优学习率,提升训练效率、降低成本。

摘要:

学习率是神经网络训练中的关键参数,合理调优的学习率可加快训练速度并提升测试准确率。本文提出一种由Lipschitz老虎机驱动的方法,用于调优神经网络的学习率。研究将该方法与广泛应用于超参数优化的主流技术HyperOpt,以及近期提出的基于老虎机的算法BLiE进行对比。针对多种神经网络架构的实验结果表明,与HyperOpt和BLiE相比,本文方法具备两点优势:a) 所需的评估次数更少;b) 每次评估的训练轮数更少。因此,该方法能够实现更高效的神经网络训练,进而降低训练时长与计算成本。

英文摘要:

Learning rate is a crucial parameter in training of neural networks. A properly tuned learning rate leads to faster training and higher test accuracy. In this paper, we propose a Lipschitz bandit-driven approach for tuning the learning rate of neural networks. The proposed approach is compared with the popular HyperOpt technique used extensively for hyperparameter optimization and the recently developed bandit-based algorithm BLiE. The results for multiple neural network architectures indicate that our method finds a better learning rate using a) fewer evaluations and b) lesser number of epochs per evaluation, when compared to both HyperOpt and BLiE. Thus, the proposed approach enables more efficient training of neural networks, leading to lower training time and lesser computational cost.

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。

↑