arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.07904stat.MLcs.LGmath.OCmath.STstat.COstat.TH
收藏

定步长SGD在非凸区域的分析:渐近正态性和偏差

An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias

University of Toronto(多伦多大学);Vector Institute(向量学院);University of California, Davis(加州大学戴维斯分校)

Lu Yu, Krishnakumar Balasubramanian, Stanislav Volgushev, Murat A. Erdogdu

摘要:

结构化非凸学习问题是统计机器学习中经常遇到的一类问题,其临界点具有良好的统计性质。数学收敛和统计估计率是很好地理解这样的问题。然而,量化与底层训练算法相关的不确定性在非凸设置中没有得到很好的研究。为了解决这个缺点,在这项工作中,我们建立了一个渐近正态性结果的恒定步长随机梯度下降(SGD)算法-在实践中广泛使用的算法。特别地,基于SGD和马尔可夫链之间的关系[DDB 19],我们证明了SGD迭代的平均值在其唯一不变分布的期望值周围渐近正态分布,只要非凸和非光滑的目标函数满足耗散性。我们还刻画了在各种局部正则条件下,期望值与目标函数临界点之间的偏差。总之,可以利用上述两个结果来构建使用SGD算法训练的非凸问题的置信区间。

英文摘要:

Structured non-convex learning problems, for which critical points have favorable statistical properties, arise frequently in statistical machine learning. Algorithmic convergence and statistical estimation rates are well-understood for such problems. However, quantifying the uncertainty associated with the underlying training algorithm is not well-studied in the non-convex setting. In order to address this shortcoming, in this work, we establish an asymptotic normality result for the constant step size stochastic gradient descent (SGD) algorithm--a widely used algorithm in practice. Specifically, based on the relationship between SGD and Markov Chains [DDB19], we show that the average of SGD iterates is asymptotically normally distributed around the expected value of their unique invariant distribution, as long as the non-convex and non-smooth objective function satisfies a dissipativity property. We also characterize the bias between this expected value and the critical points of the objective function under various local regularity conditions. Together, the above two results could be leveraged to construct confidence intervals for non-convex problems that are trained using the SGD algorithm.

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。

↑