Understanding Generalization through Visualizations
Understanding Generalization through Visualizations
复制标题
DOI：
--
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
W. R. Huang;Z. Emam;Micah Goldblum;Liam H. Fowl;J. K. Terry;Furong Huang;T. Goldstein
中科院分区：
文献类型：
--
作者：
W. R. Huang;Z. Emam;Micah Goldblum;Liam H. Fowl;J. K. Terry;Furong Huang;T. Goldstein
神经网络的强大之处在于它们能够泛化到看不见的数据，但这种现象的根本原因仍然难以捉摸。人们已经进行了许多严格的尝试来解释泛化，但可用的界限仍然相当宽松，分析并不总能带来真正的理解。这项工作的目标是使泛化更加直观。使用可视化方法，我们讨论了泛化的奥秘、损失景观的几何形状，以及维度的诅咒（或者更确切地说，祝福）如何导致优化器陷入泛化良好的最小值。
The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive. Numerous rigorous attempts have been made to explain generalization, but available bounds are still quite loose, and analysis does not always lead to true understanding. The goal of this work is to make generalization more intuitive. Using visualization methods, we discuss the mystery of generalization, the geometry of loss landscapes, and how the curse (or, rather, the blessing) of dimensionality causes optimizers to settle into minima that generalize well.