Copertina

Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kumar, Akshay, Haupt, Jarvis
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations
di: Kumar, Akshay, et al.
Pubblicazione: (2024)

Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks
di: Kumar, Akshay, et al.
Pubblicazione: (2024)

Learning Neural Networks by Neuron Pursuit
di: Kumar, Akshay, et al.
Pubblicazione: (2025)

Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks
di: Cai, Yuhang, et al.
Pubblicazione: (2025)

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
di: Min, Hancheng, et al.
Pubblicazione: (2025)

A Homogenization Approach for Gradient-Dominated Stochastic Optimization
di: Tan, Jiyuan, et al.
Pubblicazione: (2023)

Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
di: Cai, Yuhang, et al.
Pubblicazione: (2024)

Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
di: Beneventano, Pierfrancesco, et al.
Pubblicazione: (2025)

Beyond the Neural Fog: Interpretable Learning for AC Optimal Power Flow
di: Pineda, Salvador, et al.
Pubblicazione: (2024)

GANs as Gradient Flows that Converge
di: Huang, Yu-Jui, et al.
Pubblicazione: (2022)

Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
di: Bonet, Clément, et al.
Pubblicazione: (2025)

Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
di: Tucat, Matteo, et al.
Pubblicazione: (2024)

Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis
di: Cayci, Semih, et al.
Pubblicazione: (2024)

NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information
di: Tang, Wei-Ting, et al.
Pubblicazione: (2025)

Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels
di: Altekrüger, Fabian, et al.
Pubblicazione: (2023)

Abide by the Law and Follow the Flow: Conservation Laws for Gradient Flows
di: Marcotte, Sibylle, et al.
Pubblicazione: (2023)

Towards Quantifying the Hessian Structure of Neural Networks
di: Dong, Zhaorui, et al.
Pubblicazione: (2025)

Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks
di: Jnini, Anas, et al.
Pubblicazione: (2025)

Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations
di: Crăciun, Alexandru, et al.
Pubblicazione: (2025)

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
di: Zhang, Erica, et al.
Pubblicazione: (2024)

Safe Gradient Flow for Bilevel Optimization
di: Sharifi, Sina, et al.
Pubblicazione: (2025)

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

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

ATE-SG: Alternate Through the Epochs Stochastic Gradient for Multi-Task Neural Networks
di: Bellavia, Stefania, et al.
Pubblicazione: (2023)

Gradient descent in matrix factorization: Understanding large initialization
di: Chen, Hengchao, et al.
Pubblicazione: (2023)

Understanding the Implicit Regularization of Gradient Descent in Over-parameterized Models
di: Ma, Jianhao, et al.
Pubblicazione: (2025)

Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows
di: Marcotte, Sibylle, et al.
Pubblicazione: (2024)

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
di: Klein, Sara, et al.
Pubblicazione: (2023)

Towards Guided Descent: Optimization Algorithms for Training Neural Networks At Scale
di: Nagwekar, Ansh
Pubblicazione: (2025)

Unraveling the Gradient Descent Dynamics of Transformers
di: Song, Bingqing, et al.
Pubblicazione: (2024)

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

Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration
di: Tyurin, Alexander
Pubblicazione: (2025)

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
di: Yamamoto, Naoya, et al.
Pubblicazione: (2025)

Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity
di: Amortila, Philip, et al.
Pubblicazione: (2024)

Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow
di: Ren, Yinuo, et al.
Pubblicazione: (2023)

Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions
di: Varre, Aditya, et al.
Pubblicazione: (2026)

Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification
di: Anderson, Brendon G., et al.
Pubblicazione: (2021)

Stochastic Gradient Langevin Dynamics with Variance Reduction
di: Huang, Zhishen, et al.
Pubblicazione: (2021)

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
di: Lai, Kuo-Wei, et al.
Pubblicazione: (2026)

High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks
di: Martin, Simon, et al.
Pubblicazione: (2026)