When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well understood theoretically. Several previous works have attributed this success to the stochastic noise present in SGD. However, we show through a novel set of experiments that the stochastic noise is not sufficient to explain good non-convex training, and that instead the effect of a large learning rate itself is essential for obtaining best performance.We demonstrate the same effects also in the noise-less case, i.e. for full-batch GD. We formally prove that GD with large step size -- on certain non-convex function classes -- follows a different trajectory than GD with a small step size, which can lead to convergence to a global minimum instead of a local one. Our settings provide a framework for future analysis which allows comparing algorithms based on behaviors that can not be observed in the traditional settings.
翻译:当培训神经网络时,人们广泛认为,对于获得高级模型而言,大步级尺寸对于获得高级梯度底部(SGD)至关重要。然而,大步级大小对SGD成功的影响在理论上并没有得到很好的理解。前几部作品将这一成功归因于SGD中存在的随机噪音。然而,我们通过一系列新颖的实验表明,蒸汽噪音不足以解释良好的非凝固器培训,而高学习率本身对取得最佳性能至关重要。我们证明,在无噪音的情况下,即对于全批GD,也会产生同样的效果。我们正式证明,具有大步级大小的GD -- -- 在某些非convex功能类别上 -- -- 遵循的轨迹与小步级GD不同的轨迹,这可能导致全球最低程度的趋同,而不是局部的。我们的环境为今后的分析提供了一个框架,以便比较基于传统环境中无法观察到的行为的算法。