arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.03215cs.LGstat.ML
收藏

随机梯度过程与Langevin过程

Stochastic Gradient and Langevin Processes

University of California, Berkeley(加州大学伯克利分校)

Xiang Cheng, Dong Yin, Peter L. Bartlett, Michael I. Jordan

摘要:

我们证明了定量的收敛速度离散Langevin过程收敛到一个相关的随机微分方程的不变分布。我们研究了加性噪声可以是非高斯的和状态相关的,势函数可以是非凸的设置。我们表明,这些过程的关键属性取决于潜在的功能和二阶矩的加性噪声。我们将我们的理论研究结果应用于研究随机梯度下降(SGD)对非凸问题的收敛性,并使用SGD在CIFAR-10数据集上进行训练深度神经网络的实验来证实它们。

英文摘要:

We prove quantitative convergence rates at which discrete Langevin-like processes converge to the invariant distribution of a related stochastic differential equation. We study the setup where the additive noise can be non-Gaussian and state-dependent and the potential function can be non-convex. We show that the key properties of these processes depend on the potential function and the second moment of the additive noise. We apply our theoretical findings to studying the convergence of Stochastic Gradient Descent (SGD) for non-convex problems and corroborate them with experiments using SGD to train deep neural networks on the CIFAR-10 dataset.

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。

↑