arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.18519cs.LGcs.AI
收藏

改进用于大规模神经网络训练的线搜索方法

Improving Line Search Methods for Large Scale Neural Network Training

University Bielefeld(比勒费尔德大学);Technical Faculty(工学院)

Philip Kenneweg, Tristan Kenneweg, Barbara Hammer

AI总结:

本文改进了Armijo线搜索方法,通过整合ADAM动量项实现大规模神经网络的高效训练,在NLP和图像数据领域优于现有方法,并提供无超参数的PyTorch优化器。

摘要:

在最近的研究中,线搜索方法在传统随机梯度下降技术的性能上显示出显著提升,消除了对特定学习率调度的需求。在本文中,我们识别了最先进的线搜索方法中存在的问题,提出了增强措施,并严格评估了它们的有效性。我们在比以前更大的数据集和更复杂的数据领域上测试了这些方法。具体而言,我们通过将ADAM中的动量项整合到其搜索方向中来改进Armijo线搜索,从而实现高效的大规模训练,这是以前使用Armijo线搜索方法容易失败的任务。我们的优化方法优于之前的Armijo实现和Adam的调优学习率调度。我们的评估重点是在NLP和图像数据领域的Transformers和CNNs。我们的工作以Python包的形式公开提供,它提供了一个无超参数的Pytorch优化器。

英文摘要:

In recent studies, line search methods have shown significant improvements in the performance of traditional stochastic gradient descent techniques, eliminating the need for a specific learning rate schedule. In this paper, we identify existing issues in state-of-the-art line search methods, propose enhancements, and rigorously evaluate their effectiveness. We test these methods on larger datasets and more complex data domains than before. Specifically, we improve the Armijo line search by integrating the momentum term from ADAM in its search direction, enabling efficient large-scale training, a task that was previously prone to failure using Armijo line search methods. Our optimization approach outperforms both the previous Armijo implementation and tuned learning rate schedules for Adam. Our evaluation focuses on Transformers and CNNs in the domains of NLP and image data. Our work is publicly available as a Python package, which provides a hyperparameter free Pytorch optimizer.

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。

↑