arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07277cs.LGcs.NE
收藏

自适应分层超梯度下降

Adaptive Hierarchical Hyper-gradient Descent

The University of Sydney(悉尼大学)

Renlong Jie, Junbin Gao, Andrey Vasnev, Minh-Ngoc Tran

摘要:

在这项研究中,我们研究学习率自适应在不同级别的超梯度下降框架的基础上,提出了一种方法,自适应学习优化器参数相结合的多层次的学习率与层次结构。同时,我们展示了正则化过参数化学习率和在不同层次上建立自适应学习率组合之间的关系。在前馈网络、LeNet-5和ResNet-18/34等多种网络架构上的实验表明,所提出的多级自适应方法在各种情况下都能优于基线自适应方法。

英文摘要:

In this study, we investigate learning rate adaption at different levels based on the hyper-gradient descent framework and propose a method that adaptively learns the optimizer parameters by combining multiple levels of learning rates with hierarchical structures. Meanwhile, we show the relationship between regularizing over-parameterized learning rates and building combinations of adaptive learning rates at different levels. The experiments on several network architectures, including feed-forward networks, LeNet-5 and ResNet-18/34, show that the proposed multi-level adaptive approach can outperform baseline adaptive methods in a variety of circumstances.

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。

↑