arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.08311stat.MLcs.LGmath.OC
收藏

加速梯度流:风险、稳定性和隐式正则化

Accelerated Gradient Flow: Risk, Stability, and Implicit Regularization

University of Pennsylvania(宾夕法尼亚大学);Stanford University(斯坦福大学)

Yue Sheng, Alnur Ali

摘要:

加速和动量是机器学习和优化的现代应用中事实上的标准,但隐式正则化的大部分工作都集中在非加速方法上。在本文中,我们研究了Nesterov的加速梯度法和Polyak的重球法产生的迭代的统计风险,当应用于最小二乘回归时,绘制了几个连接到显式惩罚。我们在连续时间中进行分析,使我们能够做出比以前的工作更清晰的陈述,并揭示早期停止,稳定性和损失函数曲率之间的复杂相互作用。

英文摘要:

Acceleration and momentum are the de facto standard in modern applications of machine learning and optimization, yet the bulk of the work on implicit regularization focuses instead on unaccelerated methods. In this paper, we study the statistical risk of the iterates generated by Nesterov's accelerated gradient method and Polyak's heavy ball method, when applied to least squares regression, drawing several connections to explicit penalization. We carry out our analyses in continuous-time, allowing us to make sharper statements than in prior work, and revealing complex interactions between early stopping, stability, and the curvature of the loss function.

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。

↑