Image de couverture de livre

Can Entry-Wise Clipping Give Spectral Control of Stochastic Gradients?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Song, Zitao, Bai, Cedar Site, Zhang, Zhe, Bullins, Brian, Gleich, David F.
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform Convexity
par: Bai, Cedar Site, et autres
Publié: (2024)

Faster Acceleration for Steepest Descent
par: Bai, Cedar Site, et autres
Publié: (2024)

Federated Composite Saddle Point Optimization
par: Bai, Site, et autres
Publié: (2023)

Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
par: Luo, Xinyu, et autres
Publié: (2025)

Model Immunization from a Condition Number Perspective
par: Zheng, Amber Yijia, et autres
Publié: (2025)

Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points
par: Vyas, Abhijeet, et autres
Publié: (2026)

Robust Stochastic Optimization via Gradient Quantile Clipping
par: Merad, Ibrahim, et autres
Publié: (2023)

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
par: Marshall, Noah, et autres
Publié: (2024)

Dual Convexified Convolutional Neural Networks
par: Bai, Site, et autres
Publié: (2022)

Suboptimality bounds for trace-bounded SDPs enable a faster and scalable low-rank SDP solver SDPLR+
par: Huang, Yufan, et autres
Publié: (2024)

Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
par: Yukhimchuk, Alexander, et autres
Publié: (2026)

Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
par: You, Haochen, et autres
Publié: (2025)

Adaptive Gradient Clipping for Robust Federated Learning
par: Allouah, Youssef, et autres
Publié: (2024)

When Gradient Clipping Becomes a Control Mechanism for Differential Privacy in Deep Learning
par: Partohaghighi, Mohammad, et autres
Publié: (2026)

Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping
par: Liu, Zijian, et autres
Publié: (2024)

Optimal Control-Based Baseline for Guided Exploration in Policy Gradient Methods
par: Lyu, Xubo, et autres
Publié: (2020)

Does "Do Differentiable Simulators Give Better Policy Gradients?'' Give Better Policy Gradients?
par: Onoda, Ku, et autres
Publié: (2026)

Multilevel and Sequential Monte Carlo for Training-Free Diffusion Guidance
par: Gleich, Aidan, et autres
Publié: (2026)

ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
par: Zhang, Bonan, et autres
Publié: (2025)

From Gradient Clipping to Normalization for Heavy Tailed SGD
par: Hübler, Florian, et autres
Publié: (2024)

Parameter-free Clipped Gradient Descent Meets Polyak
par: Takezawa, Yuki, et autres
Publié: (2024)

Proactive Depot Discovery: A Generative Framework for Flexible Location-Routing
par: Qu, Site, et autres
Publié: (2025)

Adaptive Policy Learning Under Unknown Network Interference
par: Gleich, Aidan, et autres
Publié: (2026)

Scalable Policy Maximization Under Network Interference
par: Gleich, Aidan, et autres
Publié: (2025)

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
par: Su, Zhenpeng, et autres
Publié: (2025)

Can LLMs predict the convergence of Stochastic Gradient Descent?
par: Zekri, Oussama, et autres
Publié: (2024)

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
par: Malinovsky, Grigory, et autres
Publié: (2023)

Asynchronous Stochastic Gradient Descent with Decoupled Backpropagation and Layer-Wise Updates
par: Fokam, Cabrel Teguemne, et autres
Publié: (2024)

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing
par: Filippova, Anastasiia, et autres
Publié: (2026)

Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
par: Pethick, Thomas, et autres
Publié: (2025)

Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
par: Tucat, Matteo, et autres
Publié: (2024)

Amortized Network Intervention to Steer the Excitatory Point Processes
par: Song, Zitao, et autres
Publié: (2023)

Do Transformer World Models Give Better Policy Gradients?
par: Ma, Michel, et autres
Publié: (2024)

AGGC: Adaptive Group Gradient Clipping for Stabilizing Large Language Model Training
par: Li, Zhiyuan, et autres
Publié: (2026)

Enhancing Low-Precision Sampling via Stochastic Gradient Hamiltonian Monte Carlo
par: Wang, Ziyi, et autres
Publié: (2023)

CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
par: Su, Zhenpeng, et autres
Publié: (2025)

Equilibrium Selection in Multi-Agent Policy Gradients via Opponent-Aware Basin Entry
par: Shcherbinin, Yevhen, et autres
Publié: (2026)

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks
par: Zhang, Huiqi, et autres
Publié: (2025)

SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training
par: Soleymani, Dorsa, et autres
Publié: (2025)

Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
par: Vaswani, Sharan, et autres
Publié: (2025)