Imagen de Portada

Distributed Gradient Clustering: Convergence and the Effect of Initialization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Armacki, Aleksandar, Sharma, Himkant, Bajović, Dragana, Jakovetić, Dušan, Chakraborty, Mrityunjoy, Kar, Soummya
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Unified Framework for Center-based Clustering of Distributed Data
por: Armacki, Aleksandar, et al.
Publicado: (2024)

Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization
por: Armacki, Aleksandar, et al.
Publicado: (2025)

High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
por: Armacki, Aleksandar, et al.
Publicado: (2023)

Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry
por: Armacki, Aleksandar, et al.
Publicado: (2024)

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization
por: Armacki, Aleksandar, et al.
Publicado: (2026)

Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees
por: Armacki, Aleksandar, et al.
Publicado: (2024)

Distributed gradient methods under heavy-tailed communication noise
por: Vukovic, Manojlo, et al.
Publicado: (2025)

Tackling heavy-tailed noise in distributed estimation: Asymptotic performance and tradeoffs
por: Bajovic, Dragana, et al.
Publicado: (2026)

Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal Convergence
por: Yu, Shuhua, et al.
Publicado: (2025)

Smoothed Gradient Clipping and Error Feedback for Decentralized Optimization under Symmetric Heavy-Tailed Noise
por: Yu, Shuhua, et al.
Publicado: (2023)

High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking
por: Armacki, Aleksandar, et al.
Publicado: (2026)

High-Probability Convergence Guarantees of Decentralized SGD
por: Armacki, Aleksandar, et al.
Publicado: (2025)

Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling
por: Vukovic, Manojlo, et al.
Publicado: (2026)

Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
por: Kritharakis, Emmanouil, et al.
Publicado: (2025)

Modular Federated Learning: A Meta-Framework Perspective
por: Vicente, Frederico, et al.
Publicado: (2025)

FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning
por: Kritharakis, Emmanouil, et al.
Publicado: (2025)

Model-Free Learning and Optimal Policy Design in Multi-Agent MDPs Under Probabilistic Agent Dropout
por: Fiscko, Carmel, et al.
Publicado: (2023)

Distributed Sign Momentum with Local Steps for Training Transformers
por: Yu, Shuhua, et al.
Publicado: (2024)

Federated Multi-Objective Learning with Controlled Pareto Frontiers
por: Rao, Jiansheng, et al.
Publicado: (2025)

Convergence of Gradient Descent with Small Initialization for Unregularized Matrix Completion
por: Ma, Jianhao, et al.
Publicado: (2024)

Improving the Convergence of Private Shuffled Gradient Methods with Public Data
por: Jiang, Shuli, et al.
Publicado: (2025)

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
por: Lee, Jihoon, et al.
Publicado: (2025)

Limit Theorems for Stochastic Gradient Descent with Infinite Variance
por: Blanchet, Jose, et al.
Publicado: (2024)

On the Convergence of Multicalibration Gradient Boosting
por: Haimovich, Daniel, et al.
Publicado: (2026)

GCSAM: Gradient Centralized Sharpness Aware Minimization
por: Hassan, Mohamed, et al.
Publicado: (2025)

On the Gradient Complexity of Private Optimization with Private Oracles
por: Menart, Michael, et al.
Publicado: (2025)

Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees
por: Chen, Chuyan, et al.
Publicado: (2025)

OmniLearn: A Framework for Distributed Deep Learning over Heterogeneous Clusters
por: Tyagi, Sahil, et al.
Publicado: (2025)

Distributed Inexact Newton Method with Adaptive Step Sizes
por: Jakovetic, Dusan, et al.
Publicado: (2023)

Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees
por: Chen, Ziqin, et al.
Publicado: (2026)

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

On the Convergence Rate of LoRA Gradient Descent
por: Mu, Siqiao, et al.
Publicado: (2025)

Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence Guarantees
por: Kumar, Sawan, et al.
Publicado: (2026)

Accelerated Gradient Descent for Faster Convergence with Minimal Overhead
por: Graca, Manuel, et al.
Publicado: (2026)

Reusing Trajectories in Policy Gradients Enables Fast Convergence
por: Montenegro, Alessandro, et al.
Publicado: (2025)

Policy Gradient in Robust MDPs with Global Convergence Guarantee
por: Wang, Qiuhao, et al.
Publicado: (2022)

On the Second-Order Convergence of Biased Policy Gradient Algorithms
por: Mu, Siqiao, et al.
Publicado: (2023)

Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence
por: Xiao, Minheng, et al.
Publicado: (2024)

Distributed Harmonization: Federated Clustered Batch Effect Adjustment and Generalization
por: Hoang, Bao, et al.
Publicado: (2024)

Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization
por: Ding, Yuhao, et al.
Publicado: (2021)