We analyze the variance of stochastic gradients along negative curvature directions in certain non-convex machine learning models and show that stochastic gradients exhibit a strong component along these directions. Furthermore, we show that - contrary to the case of isotropic noise - this variance is proportional to the magnitude of the corresponding eigenvalues and not decreasing in the dimensionality. Based upon this observation we propose a new assumption under which we show that the injection of explicit, isotropic noise usually applied to make gradient descent escape saddle points can successfully be replaced by a simple SGD step. Additionally - and under the same condition - we derive the first convergence rate for plain SGD to a second-order stationary point in a number of iterations that is independent of the problem dimension.

本文研究了在某些非凸机器学习模型中，随机梯度沿负曲率方向的方差，并展示了这些方向上的随机梯度表现出强烈的分量；此外，本文提出了一种新的假设，根据这个假设，注入显式同方差噪声的普通随机梯度下降可以成功地替代梯度下降逃脱鞍点；最后，本文提出了基于相同假设的简单SGD步骤的第一个收敛率，此收敛率独立于问题的维度。

用随机梯度逃离鞍点