In the realm of deep learning, the Fisher information matrix (FIM) gives novel insights and useful tools to characterize the loss landscape, perform second-order optimization, and build geometric learning theories. The exact FIM is either unavailable in closed form or too expensive to compute. In practice, it is almost always estimated based on empirical samples. We investigate two such estimators based on two equivalent representations of the FIM -- both unbiased and consistent. Their estimation quality is naturally gauged by their variance given in closed form. We analyze how the parametric structure of a deep neural network can affect the variance. The meaning of this variance measure and its upper bounds are then discussed in the context of deep learning.
翻译:在深层学习领域,渔业信息矩阵(FIM)提供了新的洞察力和有用的工具,以说明损失情况,进行第二阶优化,并构建几何学习理论。确切的FIM要么没有封闭形式,要么过于昂贵,无法计算。在实践中,几乎总是根据经验样本估算。我们根据FIM的两个等同的表述调查了两个这样的估计数字,两个均公正且一致。其估计质量自然地以封闭形式根据其差异来衡量。我们分析了深层神经网络的参数结构如何影响差异。然后在深层学习的背景下讨论了这一差异计量的含义及其上限。