We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate efficiently the spectrum of the Hessian of modern deepnets, with tens of millions of parameters, trained on real data. Our results corroborate previous findings, based on small-scale networks, that the Hessian exhibits "spiked" behavior, with several outliers isolated from a continuous bulk. We decompose the Hessian into different components and study the dynamics with training and sample size of each term individually.
翻译:我们运用现代高维数字直线代数中最先进的工具,有效地接近现代深网赫塞尼的频谱,并有数千万参数,接受真实数据培训。 我们的结果证实了以前基于小型网络的研究结果,即赫塞伊人表现出了“尖锐”的行为,从连续体积中分离出若干异端。 我们将赫塞人分解成不同的构件,用培训和每个术语的样本大小分别研究每个术语的动态。