Cover Image

Demystifying Lazy Training of Neural Networks from a Macroscopic Viewpoint

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yuqing, Luo, Tao, Zhou, Qixuan
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers
by: Chen, Chuqi, et al.
Published: (2024)

Demystifying Distributed Training of Graph Neural Networks for Link Prediction
by: Huang, Xin, et al.
Published: (2025)

A priori Estimates for Deep Residual Network in Continuous-time Reinforcement Learning
by: Yin, Shuyu, et al.
Published: (2024)

ProPINN: Demystifying Propagation Failures in Physics-Informed Neural Networks
by: Wu, Haixu, et al.
Published: (2025)

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers
by: Shen, Xuan, et al.
Published: (2024)

Residual Attention Physics-Informed Neural Networks for Robust Multiphysics Simulation of Steady-State Electrothermal Energy Systems
by: Zhou, Yuqing, et al.
Published: (2026)

Grokking as the Transition from Lazy to Rich Training Dynamics
by: Kumar, Tanishq, et al.
Published: (2023)

PRISM: Demystifying Retention and Interaction in Mid-Training
by: Runwal, Bharat, et al.
Published: (2026)

Demystifying Oversmoothing in Attention-Based Graph Neural Networks
by: Wu, Xinyi, et al.
Published: (2023)

Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime
by: Oberweis, Noah, et al.
Published: (2025)

Demystifying Higher-Order Graph Neural Networks
by: Besta, Maciej, et al.
Published: (2024)

Has the Deep Neural Network learned the Stochastic Process? An Evaluation Viewpoint
by: Kumar, Harshit, et al.
Published: (2024)

From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
by: Dominé, Clémentine C. J., et al.
Published: (2024)

AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks
by: Mo, Shibing, et al.
Published: (2024)

Lazy FSCA for Unsupervised Variable Selection
by: Zocco, Federico, et al.
Published: (2021)

Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training
by: Wang, Ting, et al.
Published: (2025)

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
by: Tu, Zhenfeng, et al.
Published: (2024)

Demystifying Network Foundation Models
by: Beltiukov, Sylee, et al.
Published: (2025)

DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs
by: Luo, Yuebo, et al.
Published: (2025)

APEX: Probing Neural Networks via Activation Perturbation
by: Ren, Tao, et al.
Published: (2026)

Partially Lazy Gradient Descent for Smoothed Online Learning
by: Mhaisen, Naram, et al.
Published: (2026)

Phase Diagram of Initial Condensation for Two-layer Neural Networks
by: Chen, Zhengan, et al.
Published: (2023)

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

Provable Acceleration of Nesterov's Accelerated Gradient for Rectangular Matrix Factorization and Linear Neural Networks
by: Xu, Zhenghao, et al.
Published: (2024)

Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
by: Li, Shucheng, et al.
Published: (2026)

John Ellipsoids via Lazy Updates
by: Woodruff, David P., et al.
Published: (2025)

Sharpened Lazy Incremental Quasi-Newton Method
by: Lahoti, Aakash, et al.
Published: (2023)

BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training
by: Zhou, Wenjie, et al.
Published: (2025)

On the Dataless Training of Neural Networks
by: Velasquez, Alvaro, et al.
Published: (2025)

Demystify Protein Generation with Hierarchical Conditional Diffusion Models
by: Ling, Zinan, et al.
Published: (2025)

In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention
by: He, Jianliang, et al.
Published: (2025)

Frequency-adaptive Multi-scale Deep Neural Networks
by: Huang, Jizu, et al.
Published: (2024)

Flow Matching from Viewpoint of Proximal Operators
by: Fukumizu, Kenji, et al.
Published: (2026)

Demystifying Prediction Powered Inference
by: Song, Yilin, et al.
Published: (2026)

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

Gradient Rewiring for Editable Graph Neural Network Training
by: Jiang, Zhimeng, et al.
Published: (2024)

Uncertainty in Graph Neural Networks: A Survey
by: Wang, Fangxin, et al.
Published: (2024)

LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
by: Lim, Juntaek, et al.
Published: (2024)

Policy Compatible Skill Incremental Learning via Lazy Learning Interface
by: Lee, Daehee, 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)