Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks

26 May 2022

Papers citing "Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks"

6 / 6 papers shown

Title
Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization Yaoyu Zhang Leyang Zhang Zhongwang Zhang Zhiwei Bai 20 0 0 26 Jun 2024
Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion Zhiwei Bai Jiajie Zhao Yaoyu Zhang AI4CE 34 0 0 22 May 2024
Linear Stability Hypothesis and Rank Stratification for Nonlinear Models Yaoyu Zhang Zhongwang Zhang Leyang Zhang Zhiwei Bai Tao Luo Z. Xu 19 6 0 21 Nov 2022
Implicit regularization of dropout Zhongwang Zhang Zhi-Qin John Xu 19 21 0 13 Jul 2022
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 281 2,889 0 15 Sep 2016
Benefits of depth in neural networks Matus Telgarsky 142 602 0 14 Feb 2016