arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.15596cs.LGcs.CVmath.OC
收藏

深度学习优化器综述——一阶与二阶方法

A survey of deep learning optimizers -- first and second order methods

Indian Institute of Science(印度科学学院)

Rohan Kashyap

AI总结:

本文综述深度学习中 14 种常用一阶和二阶优化方法,并结合优化理论分析高维损失最小化面临的鞍点、局部极小值、Hessian 病态及算力限制等问题。

摘要:

深度学习优化涉及在权重空间中最小化一个高维损失函数;由于鞍点、局部极小值、Hessian 的病态以及计算资源有限等固有困难,这一过程通常被认为颇具难度。在本文中,我们对深度学习研究中成功使用的 14 种标准优化方法进行了全面综述,并依据优化文献对数值优化中的困难进行了理论评估。

英文摘要:

Deep Learning optimization involves minimizing a high-dimensional loss function in the weight space which is often perceived as difficult due to its inherent difficulties such as saddle points, local minima, ill-conditioning of the Hessian and limited compute resources. In this paper, we provide a comprehensive review of $14$ standard optimization methods successfully used in deep learning research and a theoretical assessment of the difficulties in numerical optimization from the optimization literature.

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。

↑