arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08680cs.LGstat.ML
收藏

形状很重要:理解噪声协方差的隐式偏差

Shape Matters: Understanding the Implicit Bias of the Noise Covariance

Stanford University(斯坦福大学);Princeton University(普林斯顿大学)

Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma

摘要:

随机梯度下降(SGD)中的噪声为训练过参数化模型提供了至关重要的隐式正则化效应。以前的理论工作主要集中在球形高斯噪声,而经验研究表明,参数相关的噪声-由小批量或标签扰动引起的-比高斯噪声更有效。本文从理论上描述了这种现象的二次参数化模型介绍Vaskevicius等人。和Woodworth et el.我们表明,在一个过参数化的设置,SGD标签噪声恢复稀疏地面真理与任意初始化,而SGD高斯噪声或梯度下降过拟合到稠密的解决方案与大的规范。我们的分析表明,参数相关的噪声引入了一个偏向局部极小值较小的噪声方差,而球面高斯噪声没有。我们项目的代码是公开的。

英文摘要:

The noise in stochastic gradient descent (SGD) provides a crucial implicit regularization effect for training overparameterized models. Prior theoretical work largely focuses on spherical Gaussian noise, whereas empirical studies demonstrate the phenomenon that parameter-dependent noise -- induced by mini-batches or label perturbation -- is far more effective than Gaussian noise. This paper theoretically characterizes this phenomenon on a quadratically-parameterized model introduced by Vaskevicius et el. and Woodworth et el. We show that in an over-parameterized setting, SGD with label noise recovers the sparse ground-truth with an arbitrary initialization, whereas SGD with Gaussian noise or gradient descent overfits to dense solutions with large norms. Our analysis reveals that parameter-dependent noise introduces a bias towards local minima with smaller noise variance, whereas spherical Gaussian noise does not. Code for our project is publicly available.

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。

↑