Empirical risk landscape analysis for understanding deep neural networks

• Main Authors: ZHOU, Pan, FENG, Jiashi
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2018
• Subjects: OS and Networks; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/9023; https://ink.library.smu.edu.sg/context/sis_research/article/10026/viewcontent/2018_ICLR_DNN_Theory.pdf
• Institution: Singapore Management University

This work aims to provide comprehensive landscape analysis of empirical risk in deep neural networks (DNNs), including the convergence behavior of its gradient, its stationary points and the empirical risk itself to their corresponding population counterparts, which reveals how various network param...