Imagen de Portada

Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Zixiang, Yang, Greg, Zhao, Qingyue, Gu, Quanquan
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Homotopy Relaxation Training Algorithms for Infinite-Width Two-Layer ReLU Neural Networks
por: Yang, Yahong, et al.
Publicado: (2023)

Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent
por: Kou, Yiwen, et al.
Publicado: (2024)

A Dual Certificate Approach to Sparsity in Infinite-Width Shallow Neural Networks
por: Del Grande, Leonardo, et al.
Publicado: (2026)

On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization
por: Zhou, Dongruo, et al.
Publicado: (2018)

Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers
por: Li, Runjia, et al.
Publicado: (2024)

Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning
por: Caron, Francois, et al.
Publicado: (2023)

A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
por: Zhao, Heyang, et al.
Publicado: (2023)

Global Convergence of SGD On Two Layer Neural Nets
por: Gopalani, Pulkit, et al.
Publicado: (2022)

Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
por: Zhang, Shiyuan, et al.
Publicado: (2026)

Grassmannian Geometry and Global Convergence of Variable Projection for Neural Networks
por: Dus, Mathias
Publicado: (2026)

Global Convergence of Four-Layer Matrix Factorization under Random Initialization
por: Luo, Minrui, et al.
Publicado: (2025)

Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets
por: Gopalani, Pulkit, et al.
Publicado: (2023)

Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
por: Di, Qiwei, et al.
Publicado: (2023)

Feel-Good Thompson Sampling for Contextual Dueling Bandits
por: Li, Xuheng, et al.
Publicado: (2024)

Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits
por: Li, Xuheng, et al.
Publicado: (2025)

Understanding SGD with Exponential Moving Average: A Case Study in Linear Regression
por: Li, Xuheng, et al.
Publicado: (2025)

Towards a Principled Muon under $μ\mathsf{P}$: Ensuring Spectral Conditions throughout Training
por: Zhao, John
Publicado: (2026)

Global Contact-Rich Planning with Sparsity-Rich Semidefinite Relaxations
por: Kang, Shucheng, et al.
Publicado: (2025)

Nesterov Flow May Travel Infinitely Long to Converge to a Minimizer
por: Ryu, Ernest K.
Publicado: (2026)

Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks
por: Xu, Xianliang, et al.
Publicado: (2024)

Quantized Distributed Nonconvex Optimization Algorithms with Linear Convergence under the Polyak--$Ł$ojasiewicz Condition
por: Xu, Lei, et al.
Publicado: (2022)

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
por: Zhang, Junkai, et al.
Publicado: (2023)

MARS-M: When Variance Reduction Meets Matrices
por: Liu, Yifeng, et al.
Publicado: (2025)

Convergence of Policy Gradient for Stochastic Linear-Quadratic Control Problem in Infinite Horizon
por: Zhang, Xinpei, et al.
Publicado: (2024)

Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking
por: Kolomvaki, Afroditi, et al.
Publicado: (2026)

Policy Gradient Methods for the Cost-Constrained LQR: Strong Duality and Global Convergence
por: Zhao, Feiran, et al.
Publicado: (2024)

Non-Parametric Learning of Stochastic Differential Equations with Non-asymptotic Fast Rates of Convergence
por: Bonalli, Riccardo, et al.
Publicado: (2023)

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

Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
por: Meng, Yiming, et al.
Publicado: (2024)

Global Convergence and Error Propagation in Neural Gradient Flows: A Riemannian Optimization Framework
por: Zheng, Shixin, et al.
Publicado: (2026)

On the Nonsmooth Geometry and Neural Approximation of the Optimal Value Function of Infinite-Horizon Pendulum Swing-up
por: Han, Haoyu, et al.
Publicado: (2023)

Optimization for Neural Operators can Benefit from Width
por: Cisneros-Velarde, Pedro, et al.
Publicado: (2025)

Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Feature Learning by Learnable Channel Attention
por: Yang, Yingzhen
Publicado: (2025)

(Corrected Version) Push-LSVRG-UP: Distributed Stochastic Optimization over Unbalanced Directed Networks with Uncoordinated Triggered Probabilities
por: Hu, Jinhui, et al.
Publicado: (2023)

Reinforcement Learning from Human Feedback with Active Queries
por: Ji, Kaixuan, et al.
Publicado: (2024)

Design of Transit Networks: Global Optimization of Continuous Approximation Models via Geometric Programming
por: Mao, Haoyang, et al.
Publicado: (2026)

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

Optimality-Informed Neural Networks for Solving Parametric Optimization Problems
por: Hoffmann, Matthias K., et al.
Publicado: (2025)

$\ell_{1\text{-}2}$ Regularization for Sparse Optimization: Consistency and Global Convergence
por: Hu, Yaohua, et al.
Publicado: (2026)

Learning Parametric Convex Functions
por: Schaller, Maximilian, et al.
Publicado: (2025)