In the machine learning literature stochastic gradient descent has recently been widely discussed for its purported implicit regularization properties. Much of the theory, that attempts to clarify the role of noise in stochastic gradient algorithms, has widely approximated stochastic gradient descent by a stochastic differential equation with Gaussian noise. We provide a novel rigorous theoretical justification for this practice that showcases how the Gaussianity of the noise arises naturally.
翻译:在机器学习文献中,人们最近就其所谓的隐性正规化特性进行了广泛讨论。 大部分试图澄清噪音在随机梯度算法中作用的理论,通过与高山噪音的随机差异方程式,广泛接近于随机梯度梯度梯度下降。 我们为这种做法提供了一个新的严格理论理由,展示了噪音的高斯度是如何自然产生的。