Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bai, Zhiwei, Luo, Tao, Xu, Zhi-Qin John, Zhang, Yaoyu
Format:	Preprint
Published:	2022
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
by: Xu, Zhi-Qin John, et al.
Published: (2019)

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
by: Zhang, Yaoyu, et al.
Published: (2024)

Loss Jump During Loss Switch in Solving PDEs with Neural Networks
by: Wang, Zhiwei, et al.
Published: (2024)

Overview frequency principle/spectral bias in deep learning
by: Xu, Zhi-Qin John, et al.
Published: (2022)

Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting
by: Zhang, Leyang, et al.
Published: (2025)

Loss Spike in Training Neural Networks
by: Li, Xiaolong, et al.
Published: (2023)

Adaptive Preconditioners Trigger Loss Spikes in Adam
by: Bai, Zhiwei, et al.
Published: (2025)

Embedding principle of homogeneous neural network for classification problem
by: Zhang, Jiahan, et al.
Published: (2025)

Geometry and Local Recovery of Global Minima of Two-layer Neural Networks at Overparameterization
by: Zhang, Leyang, et al.
Published: (2023)

Geometry of Critical Sets and Existence of Saddle Branches for Two-layer Neural Networks
by: Zhang, Leyang, et al.
Published: (2024)

Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks
by: Xu, Yichu, et al.
Published: (2024)

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
by: Zhang, Zhongwang, et al.
Published: (2024)

Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
by: Bai, Zhiwei, et al.
Published: (2024)

Disentangle Sample Size and Initialization Effect on Perfect Generalization for Single-Neuron Target
by: Zhao, Jiajie, et al.
Published: (2024)

An overview of condensation phenomenon in deep learning
by: Xu, Zhi-Qin John, et al.
Published: (2025)

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
by: Zhang, Zhongwang, et al.
Published: (2025)

Visualization and Analysis of the Loss Landscape in Graph Neural Networks
by: Moustafa, Samir, et al.
Published: (2025)

Efficient and Flexible Method for Reducing Moderate-size Deep Neural Networks with Condensation
by: Chen, Tianyi, et al.
Published: (2024)

A rationale from frequency perspective for grokking in training neural network
by: Zhou, Zhangchen, et al.
Published: (2024)

Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding
by: Wu, Frank Zhengqing, et al.
Published: (2024)

Classification with Deep Neural Networks and Logistic Loss
by: Zhang, Zihan, et al.
Published: (2023)

Sensitivity Analysis On Loss Landscape
by: Faroz, Salman
Published: (2024)

Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
by: Fang, Kun, et al.
Published: (2023)

Probability Signature: Bridging Data Semantics and Embedding Structure in Language Models
by: Yao, Junjie, et al.
Published: (2025)

A Unified Theory of Quantum Neural Network Loss Landscapes
by: Anschuetz, Eric R.
Published: (2024)

Loss Landscape Characterization of Neural Networks without Over-Parametrization
by: Islamov, Rustem, et al.
Published: (2024)

Paths and Ambient Spaces in Neural Loss Landscapes
by: Dold, Daniel, et al.
Published: (2025)

On Multi-Stage Loss Dynamics in Neural Networks: Mechanisms of Plateau and Descent Stages
by: Chen, Zheng-An, et al.
Published: (2024)

Layer Embedding Deep Fusion Graph Neural Network
by: Xu, Taihua, et al.
Published: (2026)

Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis
by: Chen, Jiaqing, et al.
Published: (2026)

Depth-induced NTK: Bridging Over-parameterized Neural Networks and Deep Neural Kernels
by: Tian, Yong-Ming, et al.
Published: (2025)

Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems
by: Luo, Xiangzhong, et al.
Published: (2025)

Focus and Dilution: The Multi-stage Learning Process of Attention
by: Chen, Zheng-An, et al.
Published: (2026)

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data
by: Chen, Tianyi, et al.
Published: (2025)

On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness
by: Kamber, Anil, et al.
Published: (2026)

Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks
by: Qin, Zhen, et al.
Published: (2023)

Neural Force Field: Few-shot Learning of Generalized Physical Reasoning
by: Li, Shiqian, et al.
Published: (2025)

Investigating the Gestalt Principle of Closure in Deep Convolutional Neural Networks
by: Zhang, Yuyan, et al.
Published: (2024)

Feature Dynamics as Implicit Data Augmentation: A Depth-Decomposed View on Deep Neural Network Generalization
by: Ruan, Tianyu, et al.
Published: (2025)

Flat Channels to Infinity in Neural Loss Landscapes
by: Martinelli, Flavio, et al.
Published: (2025)