Semi-flat minima and saddle points by embedding neural networks to
overparameterization

v1v2 (latest)

Semi-flat minima and saddle points by embedding neural networks to overparameterization

12 June 2019

Shoichiro Yamaguchi

Yoh-ichi Mototake

ArXiv (abs)PDF HTML

Papers citing "Semi-flat minima and saddle points by embedding neural networks to overparameterization"

10 / 10 papers shown

Title
Flat Channels to Infinity in Neural Loss Landscapes Flavio Martinelli Alexander Van Meegen Berfin Simsek W. Gerstner Johanni Brea 10 0 0 17 Jun 2025
Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion Zhiwei Bai Jiajie Zhao Yaoyu Zhang AI4CE 98 0 0 22 May 2024
Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding Zhengqing Wu Berfin Simsek Francois Ged ODL 117 0 0 08 Feb 2024
Loss Spike in Training Neural Networks Zhongwang Zhang Z. Xu 72 7 0 20 May 2023
Linear Stability Hypothesis and Rank Stratification for Nonlinear Models Yaoyu Zhang Zhongwang Zhang Leyang Zhang Zhiwei Bai Yaoyu Zhang Z. Xu 56 8 0 21 Nov 2022
Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks Zhiwei Bai Yaoyu Zhang Z. Xu Yaoyu Zhang 122 6 0 26 May 2022
Embedding Principle: a hierarchical structure of loss landscape of deep neural networks Yaoyu Zhang Yuqing Li Zhongwang Zhang Yaoyu Zhang Z. Xu 82 23 0 30 Nov 2021
Embedding Principle of Loss Landscape of Deep Neural Networks Yaoyu Zhang Zhongwang Zhang Yaoyu Zhang Z. Xu 67 38 0 30 May 2021
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances Berfin cSimcsek François Ged Arthur Jacot Francesco Spadaro Clément Hongler W. Gerstner Johanni Brea AI4CE 87 102 0 25 May 2021
Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited Wesley J. Maddox Gregory W. Benton A. Wilson 136 61 0 04 Mar 2020