Copertina

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Luo, Ruichen, Stich, Sebastian U, Horváth, Samuel, Takáč, Martin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Optimization and Control Distributed, Parallel, and Cluster Computing Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication
di: Patel, Kumar Kshitij, et al.
Pubblicazione: (2024)

Efficient Gradient Methods for Distributed Saddle Problems
di: Luo, Ruichen, et al.
Pubblicazione: (2026)

Birch SGD: A Tree Graph Framework for Local and Asynchronous SGD Methods
di: Tyurin, Alexander, et al.
Pubblicazione: (2025)

LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
di: Maziane, Yassine, et al.
Pubblicazione: (2026)

Local Methods with Adaptivity via Scaling
di: Chezhegov, Savelii, et al.
Pubblicazione: (2024)

MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times
di: Maranjyan, Artavazd, et al.
Pubblicazione: (2024)

On Biased Compression for Distributed Learning
di: Beznosikov, Aleksandr, et al.
Pubblicazione: (2020)

Demystifying Why Local Aggregation Helps: Convergence Analysis of Hierarchical SGD
di: Wang, Jiayi, et al.
Pubblicazione: (2020)

Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity
di: Maranjyan, Artavazd, et al.
Pubblicazione: (2025)

First Provably Optimal Asynchronous SGD for Homogeneous and Heterogeneous Data
di: Maranjyan, Artavazd
Pubblicazione: (2026)

Decentralized Personalized Federated Learning for Min-Max Problems
di: Borodich, Ekaterina, et al.
Pubblicazione: (2021)

Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
di: Mahran, Ammar, et al.
Pubblicazione: (2026)

Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity
di: Maranjyan, Artavazd, et al.
Pubblicazione: (2025)

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities
di: Beznosikov, Aleksandr, et al.
Pubblicazione: (2023)

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
di: Malinovsky, Grigory, et al.
Pubblicazione: (2023)

On Principled Local Optimization Methods for Federated Learning
di: Yuan, Honglin
Pubblicazione: (2024)

Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps
di: Yang, Junchi, et al.
Pubblicazione: (2024)

FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning
di: Tastan, Nurbek, et al.
Pubblicazione: (2024)

GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity
di: Maranjyan, Artavazd, et al.
Pubblicazione: (2022)

Communication-Efficient Federated Bilevel Optimization with Local and Global Lower Level Problems
di: Li, Junyi, et al.
Pubblicazione: (2023)

LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression
di: Condat, Laurent, et al.
Pubblicazione: (2024)

Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction
di: Tovmasyan, Zhirayr, et al.
Pubblicazione: (2026)

Continuous-Time Analysis of Federated Averaging
di: Overman, Tom, et al.
Pubblicazione: (2025)

Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation
di: Liao, Fangshuo, et al.
Pubblicazione: (2025)

Rate Analysis of Coupled Distributed Stochastic Approximation for Misspecified Optimization
di: Yang, Yaqun, et al.
Pubblicazione: (2024)

FedCanon: Non-Convex Composite Federated Learning with Efficient Proximal Operation on Heterogeneous Data
di: Zhou, Yuan, et al.
Pubblicazione: (2025)

Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
di: Sadiev, Abdurakhmon, et al.
Pubblicazione: (2026)

Decentralized Directed Collaboration for Personalized Federated Learning
di: Liu, Yingqi, et al.
Pubblicazione: (2024)

Stochastic Controlled Averaging for Federated Learning with Communication Compression
di: Huang, Xinmeng, et al.
Pubblicazione: (2023)

High-Performance Hybrid Algorithm for Minimum Sum-of-Squares Clustering of Infinitely Tall Data
di: Mussabayev, Ravil, et al.
Pubblicazione: (2023)

Time-varying Mixing Matrix Design for Energy-efficient Decentralized Federated Learning
di: Zhang, Xusheng, et al.
Pubblicazione: (2025)

A Stochastic Approximation Approach for Efficient Decentralized Optimization on Random Networks
di: Yau, Chung-Yiu, et al.
Pubblicazione: (2024)

Tight analyses of first-order methods with error feedback
di: Thomsen, Daniel Berg, et al.
Pubblicazione: (2025)

Convergence of Sign-based Random Reshuffling Algorithms for Nonconvex Optimization
di: Qin, Zhen, et al.
Pubblicazione: (2023)

Accelerated Methods with Compressed Communications for Distributed Optimization Problems under Data Similarity
di: Bylinkin, Dmitry, et al.
Pubblicazione: (2024)

BROADCAST: Reducing Both Stochastic and Compression Noise to Robustify Communication-Efficient Federated Learning
di: Zhu, Heng, et al.
Pubblicazione: (2021)

Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape
di: Sun, Yan, et al.
Pubblicazione: (2023)

Optimizing Stochastic Gradient Push under Broadcast Communications
di: Nguyen, Tuan, et al.
Pubblicazione: (2026)

Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability
di: Xiang, Ming, et al.
Pubblicazione: (2024)

Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
di: Huang, Yan, et al.
Pubblicazione: (2024)