Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints
Wenlong Mou Thanks: Affiliation: Key Laboratory of Machine Perception, School of EECS, Peking University Liwei Wang Thanks: Affiliation: Key Laboratory of Machine Perception, School of EECS, Peking University Xiyu Zhai Thanks: Affiliation: School of Mathematics, University of Science and Technology of China Kai Zheng Thanks: Affiliation: Key Laboratory of Machine Perception, School of EECS, Peking University
Abstract
Algorithm-dependent generalization error bounds are central to statistical learning theory. A learning algorithm may use a large hypothesis space, but the limited number of iterations controls its model capacity and generalization error. The impacts of stochastic gradient methods on generalization error for non-convex learning problems not only have important theoretical consequences, but are also critical to generalization errors of deep learning.
原文 arXiv:1707.05947;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1707.05947v1