Imagen de Portada

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Yaoyu, Zhang, Leyang, Zhang, Zhongwang, Bai, Zhiwei
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

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

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

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
por: Bai, Zhiwei, et al.
Publicado: (2022)

Sharp Global Guarantees for Nonconvex Low-rank Recovery in the Noisy Overparameterized Regime
por: Zhang, Richard Y.
Publicado: (2021)

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

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

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

Linear Independence of Generalized Neurons and Related Functions
por: Zhang, Leyang
Publicado: (2024)

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

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

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

Improved Global Guarantees for the Nonconvex Burer--Monteiro Factorization via Rank Overparameterization
por: Zhang, Richard Y.
Publicado: (2022)

Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
por: Giampouras, Paris, et al.
Publicado: (2024)

How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks?
por: Alon, Gal, et al.
Publicado: (2025)

Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks
por: Zhang, Shihao, et al.
Publicado: (2025)

A Recovery Guarantee for Sparse Neural Networks
por: Fridovich-Keil, Sara, et al.
Publicado: (2025)

Convergence and Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems
por: Buskulic, Nathan, et al.
Publicado: (2023)

Implicit Regularization and Generalization in Overparameterized Neural Networks
por: Johannsen, Zeran
Publicado: (2026)

Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks
por: Adeoye, Adeyemi D., et al.
Publicado: (2024)

Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
por: Zhang, Zixuan, et al.
Publicado: (2023)

Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
por: Riedl, Konstantin, et al.
Publicado: (2026)

Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics
por: Kwon, Soo Min, et al.
Publicado: (2023)

Overparameterized Multiple Linear Regression as Hyper-Curve Fitting
por: Atza, E., et al.
Publicado: (2024)

LUNA: Linear Universal Neural Attention with Generalization Guarantees
por: Shahbazi, Ashkan, et al.
Publicado: (2025)

Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems trained with Gradient Descent
por: Buskulic, Nathan, et al.
Publicado: (2024)

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
por: Peleg, Amit, et al.
Publicado: (2024)

Task Shift: From Classification to Regression in Overparameterized Linear Models
por: LaBonte, Tyler, et al.
Publicado: (2025)

Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models
por: Wu, David X., et al.
Publicado: (2023)

Provable Generalization in Overparameterized Neural Nets
por: Dhingra, Aviral
Publicado: (2025)

Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
por: Wang, Zhiwei, et al.
Publicado: (2024)

Learning Guarantee of Reward Modeling Using Deep Neural Networks
por: Luo, Yuanhang, et al.
Publicado: (2025)

The Role of Symmetry in Optimizing Overparameterized Networks
por: Sareen, Kusha, et al.
Publicado: (2026)

Analysis of Overparameterization in Continual Learning under a Linear Model
por: Goldfarb, Daniel, et al.
Publicado: (2025)

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

Guaranteeing Conservation of Integrals with Projection in Physics-Informed Neural Networks
por: Baez, Anthony, et al.
Publicado: (2025)

Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
por: Di Carlo, Luca, et al.
Publicado: (2025)

Guaranteeing Conservation Laws with Projection in Physics-Informed Neural Networks
por: Baez, Anthony, et al.
Publicado: (2024)

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

Solving Inverse Problems with Deep Linear Neural Networks: Global Convergence Guarantees for Gradient Descent with Weight Decay
por: Laus, Hannah, et al.
Publicado: (2025)