arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2007.01219eess.SPcs.LG
收藏

随机优化问题中基于自适应批量的速率和方差平衡算法

Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems

University of Pennsylvania(宾夕法尼亚大学);U.S. Army Research Laboratory(美国陆军研究实验室)

Zhan Gao, Alec Koppel, Alejandro Ribeiro

摘要:

随机梯度下降是解决随机优化问题的经典工具,是现代机器学习和统计学的基石。在这项工作中,我们试图平衡的事实,衰减步长是需要精确的渐近收敛的事实,恒定的步长学习速度更快,在有限的时间内的错误。要做到这一点,而不是固定的小批量和步长在一开始,我们提出了一个策略,允许参数自适应地演变。具体而言,批量大小被设置为分段常数递增序列,其中当满足合适的误差准则时发生递增。此外,步长被选择为产生最快收敛的步长。整体算法,双尺度自适应(TSA)计划,开发凸和非凸随机优化问题。它继承了随机梯度法的精确渐近收敛性。更重要的是,在理论上实现了最佳的误差减少率,以及在计算成本的整体减少。实验上,我们观察到TSA相对于标准SGD获得了有利的折衷,标准SGD固定了小批量和步长,或者简单地允许一个分别增加或减少。

英文摘要:

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics. In this work, we seek to balance the fact that attenuating step-size is required for exact asymptotic convergence with the fact that constant step-size learns faster in finite time up to an error. To do so, rather than fixing the mini-batch and the step-size at the outset, we propose a strategy to allow parameters to evolve adaptively. Specifically, the batch-size is set to be a piecewise-constant increasing sequence where the increase occurs when a suitable error criterion is satisfied. Moreover, the step-size is selected as that which yields the fastest convergence. The overall algorithm, two scale adaptive (TSA) scheme, is developed for both convex and non-convex stochastic optimization problems. It inherits the exact asymptotic convergence of stochastic gradient method. More importantly, the optimal error decreasing rate is achieved theoretically, as well as an overall reduction in computational cost. Experimentally, we observe that TSA attains a favorable tradeoff relative to standard SGD that fixes the mini-batch and the step-size, or simply allowing one to increase or decrease respectively.

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。

↑