Improved generalisation bounds for deep learning through L∞ covering numbers

• Main Authors: LEDENT, Antoine, LEI, Yunwen, KLOFT, Marius
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2019
• 主題: Deep Learning; convolutions; multi-class; multi-label; Databases and Information Systems; Graphics and Human Computer Interfaces
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/7211; https://ink.library.smu.edu.sg/context/sis_research/article/8214/viewcontent/85_wrshpnew.pdf
• 機構: Singapore Management University

Using proof techniques involving L∞ covering numbers, we show generalisation error bounds for deep learning with two main improvements over the state of the art. First, our bounds have no explicit dependence on the number of classes except for logarithmic factors. This holds even when formulating th...