In recent years, various notions of capacity and complexity have been proposed for characterizing the generalization properties of stochastic gradient descent (SGD) in deep learning. Some of the popular notions that correlate well with the performance on unseen data are (i) the `flatness' of the local minimum found by SGD, which is related to the eigenvalues of the Hessian, (ii) the ratio of the stepsize $\eta$ to the batch size $b$, which essentially controls the magnitude of the stochastic gradient noise, and (iii) the `tail-index', which measures the heaviness of the tails of the eigenspectra of the network weights. In this paper, we argue that these three seemingly unrelated perspectives for generalization are deeply linked to each other. We claim that depending on the structure of the Hessian of the loss at the minimum, and the choices of the algorithm parameters $\eta$ and $b$, the SGD iterates will converge to a \emph{heavy-tailed} stationary distribution. We rigorously prove this claim in the setting of linear regression: we show that even in a simple quadratic optimization problem with independent and identically distributed Gaussian data, the iterates can be heavy-tailed with infinite variance. We further characterize the behavior of the tails with respect to algorithm parameters, the dimension, and the curvature. We then translate our results into insights about the behavior of SGD in deep learning. We finally support our theory with experiments conducted on both synthetic data and neural networks. To our knowledge, these results are the first of their kind to rigorously characterize the empirically observed heavy-tailed behavior of SGD.

本文阐述了随机梯度下降（SGD）在深度学习中的泛化性能与最小值的浅奥关系，并通过线性回归等简单问题分析证明了参数选择会对算法的收敛率及概率分布产生影响。

随机梯度下降中的重尾现象