{"total":107,"rows":[{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134,"area":null},{"id":"2202.03836","title":"An Improved Analysis of Gradient Tracking for Decentralized Machine Learning","created":"2022-02-08","cited_by_count":69,"area":null},{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56,"area":null},{"id":"2201.13320","title":"BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression","created":"2022-01-31","cited_by_count":41,"area":null},{"id":"2110.04175","title":"RelaySum for Decentralized Deep Learning on Heterogeneous Data","created":"2021-10-08","cited_by_count":39,"area":null},{"id":"2306.16504","title":"Momentum Benefits Non-IID Federated Learning Simply and Provably","created":"2023-06-28","cited_by_count":38,"area":null},{"id":"2102.07091","title":"Decentralized Riemannian Gradient Descent on the Stiefel Manifold","created":"2021-02-14","cited_by_count":33,"area":null},{"id":"2301.01313","title":"Decentralized Gradient Tracking with Local Steps","created":"2023-01-03","cited_by_count":32,"area":null},{"id":"2105.08023","title":"Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD","created":"2021-05-17","cited_by_count":29,"area":null},{"id":"2206.03093","title":"Beyond spectral gap: The role of the topology in decentralized learning","created":"2022-06-07","cited_by_count":27,"area":null},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25,"area":null},{"id":"2210.07881","title":"Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate","created":"2022-10-14","cited_by_count":25,"area":null},{"id":"2210.07863","title":"Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization","created":"2022-10-14","cited_by_count":23,"area":null},{"id":"2102.06752","title":"A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization","created":"2021-02-12","cited_by_count":21,"area":null},{"id":"2210.04757","title":"On the Performance of Gradient Tracking with Local Updates","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2210.12839","title":"Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity","created":"2022-10-23","cited_by_count":21,"area":null},{"id":"2209.15505","title":"Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data","created":"2022-09-30","cited_by_count":20,"area":null},{"id":"2109.03194","title":"On the Convergence of Decentralized Adaptive Gradient Methods","created":"2021-09-07","cited_by_count":17,"area":null},{"id":"2110.12347","title":"Acceleration in Distributed Optimization under Similarity","created":"2021-10-24","cited_by_count":17,"area":null},{"id":"2110.01165","title":"DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization","created":"2021-10-04","cited_by_count":16,"area":null},{"id":"2111.04287","title":"BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning","created":"2021-11-08","cited_by_count":16,"area":null},{"id":"2107.11304","title":"Finite-Bit Quantization For Distributed Algorithms With Linear Convergence","created":"2021-07-23","cited_by_count":15,"area":null},{"id":"2105.04851","title":"Improving the Transient Times for Distributed Stochastic Gradient Methods","created":"2021-05-11","cited_by_count":13,"area":null},{"id":"2204.06477","title":"Data-heterogeneity-aware Mixing for Decentralized Learning","created":"2022-04-13","cited_by_count":12,"area":null},{"id":"2305.04792","title":"Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2104.02596","title":"Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization","created":"2021-04-06","cited_by_count":11,"area":null},{"id":"2112.14949","title":"Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function","created":"2021-12-30","cited_by_count":11,"area":null},{"id":"2207.03730","title":"Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology","created":"2022-07-08","cited_by_count":10,"area":null},{"id":"2210.13767","title":"Networked Signal and Information Processing","created":"2022-10-25","cited_by_count":10,"area":null},{"id":"2212.07534","title":"Decentralized Nonconvex Optimization with Guaranteed Privacy and Accuracy","created":"2022-12-14","cited_by_count":10,"area":null},{"id":"2503.14353","title":"Unified Analysis of Decentralized Gradient Descent: a Contraction Mapping Framework","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2305.09896","title":"Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2305.11420","title":"Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence","created":"2023-05-19","cited_by_count":9,"area":null},{"id":"2101.01300","title":"A Linearly Convergent Algorithm for Distributed Principal Component Analysis","created":"2021-01-05","cited_by_count":8,"area":null},{"id":"2105.01231","title":"GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning","created":"2021-05-04","cited_by_count":8,"area":null},{"id":"2108.04448","title":"Decentralized Composite Optimization with Compression","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2112.15287","title":"Distributed Random Reshuffling over Networks","created":"2021-12-31","cited_by_count":7,"area":null},{"id":"2311.08945","title":"A Single-Loop Algorithm for Decentralized Bilevel Optimization","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2403.15654","title":"The Effectiveness of Local Updates for Decentralized Learning under Data Heterogeneity","created":"2024-03-23","cited_by_count":7,"area":null},{"id":"2409.18448","title":"Hierarchical Federated Learning with Multi-Timescale Gradient Correction","created":"2024-09-27","cited_by_count":7,"area":null},{"id":"2202.00255","title":"DoCoM: Compressed Decentralized Optimization with Near-Optimal Sample Complexity","created":"2022-02-01","cited_by_count":6,"area":null},{"id":"2212.02387","title":"An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2306.00256","title":"DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2302.03238","title":"Decentralized Inexact Proximal Gradient Method With Network-Independent Stepsizes for Convex Composite Optimization","created":"2023-02-07","cited_by_count":5,"area":null},{"id":"2103.06406","title":"Distributed Principal Subspace Analysis for Partitioned Big Data: Algorithms, Analysis, and Implementation","created":"2021-03-11","cited_by_count":4,"area":null},{"id":"2107.07211","title":"Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian Monte Carlo","created":"2021-07-15","cited_by_count":4,"area":null},{"id":"2211.00533","title":"Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2302.09766","title":"A One-Sample Decentralized Proximal Algorithm for Non-Convex Stochastic Composite Optimization","created":"2023-02-20","cited_by_count":4,"area":null},{"id":"2304.10902","title":"Near-Optimal Decentralized Momentum Method for Nonconvex-PL Minimax Problems","created":"2023-04-21","cited_by_count":4,"area":null},{"id":"2306.05100","title":"Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates","created":"2023-06-08","cited_by_count":4,"area":null},{"id":"2510.01377","title":"DeMuon: A Decentralized Muon for Matrix Optimization over Graphs","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2511.12836","title":"DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks","created":"2025-11-16","cited_by_count":4,"area":null},{"id":"2108.12373","title":"FAST-PCA: A Fast and Exact Algorithm for Distributed Principal Component Analysis","created":"2021-08-27","cited_by_count":3,"area":null},{"id":"2202.05812","title":"Distributed saddle point problems for strongly concave-convex functions","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2111.03820","title":"Distributed stochastic proximal algorithm with random reshuffling for non-smooth finite-sum optimization","created":"2021-11-06","cited_by_count":2,"area":null},{"id":"2202.03346","title":"Variance reduced stochastic optimization over directed graphs with row and column stochastic weights","created":"2022-02-07","cited_by_count":2,"area":null},{"id":"2204.12663","title":"Understanding A Class of Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective","created":"2022-04-27","cited_by_count":2,"area":null},{"id":"2205.03779","title":"Communication Compression for Decentralized Learning with Operator Splitting Methods","created":"2022-05-08","cited_by_count":2,"area":null},{"id":"2210.05618","title":"Zero-Order One-Point Estimate with Distributed Stochastic Gradient-Tracking Technique","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2307.07113","title":"Variance-reduced accelerated methods for decentralized stochastic double-regularized nonconvex strongly-concave minimax problems","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2307.11617","title":"Robust Fully-Asynchronous Methods for Distributed Training over General Architecture","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2311.18787","title":"Communication-Efficient Federated Optimization over Semi-Decentralized Networks","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2312.11861","title":"A Proximal Gradient Method With Probabilistic Multi-Gossip Communications for Decentralized Composite Optimization","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2402.18018","title":"Communication Efficient ConFederated Learning: An Event-Triggered SAGA Approach","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2502.02727","title":"Gradient Correction in Federated Learning with Adaptive Optimization","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2508.04950","title":"Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2103.15664","title":"Competing Adaptive Networks","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2107.12065","title":"Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs","created":"2021-07-26","cited_by_count":1,"area":null},{"id":"2111.06530","title":"Distributed Sparse Regression via Penalization","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2205.11979","title":"Theoretical Analysis of Primal-Dual Algorithm for Non-Convex Stochastic Decentralized Optimization","created":"2022-05-23","cited_by_count":1,"area":null},{"id":"2302.04151","title":"Policy Evaluation in Decentralized POMDPs with Belief Sharing","created":"2023-02-08","cited_by_count":1,"area":null},{"id":"2303.17779","title":"Decentralized Weakly Convex Optimization Over the Stiefel Manifold","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2306.13892","title":"Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensus","created":"2023-06-24","cited_by_count":1,"area":null},{"id":"2403.11565","title":"Convergence of Decentralized Stochastic Subgradient-based Methods for Nonsmooth Nonconvex functions","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2408.09775","title":"Faster Adaptive Decentralized Learning Algorithms","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2410.05942","title":"Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2410.19319","title":"Fully First-Order Methods for Decentralized Bilevel Optimization","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2506.00961","title":"Enhancing Parallelism in Decentralized Stochastic Convex Optimization","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2506.05791","title":"Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2506.07351","title":"Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2509.14488","title":"Decentralized Optimization with Topology-Independent Communication","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2510.06141","title":"High-Probability Convergence Guarantees of Decentralized SGD","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2601.07021","title":"Tight Analysis of Decentralized SGD: A Markov Chain Perspective","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2606.07496","title":"Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.09154","title":"Improved Convergence Analysis of Topology Dependence in Decentralized SGD","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2110.04523","title":"An Empirical Study on Compressed Decentralized Stochastic Gradient Algorithms with Overparameterized Models","created":"2021-10-09","cited_by_count":0,"area":null},{"id":"2303.00179","title":"A Unified Momentum-based Paradigm of Decentralized SGD for Non-Convex Models and Heterogeneous Data","created":"2023-03-01","cited_by_count":0,"area":null},{"id":"2304.07358","title":"Exact Subspace Diffusion for Decentralized Multitask Learning","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2309.02626","title":"Adaptive Consensus: A network pruning approach for decentralized optimization","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2402.01302","title":"A Unified Framework for Center-based Clustering of Distributed Data","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2404.15273","title":"Estimation Network Design framework for efficient distributed optimization","created":"2024-04-23","cited_by_count":0,"area":null},{"id":"2407.16728","title":"Distributed Difference of Convex Optimization","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2409.15680","title":"Distributed Online Bandit Nonconvex Optimization with One-Point Residual Feedback via Dynamic Regret","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2410.18774","title":"A Stochastic Approximation Approach for Efficient Decentralized Optimization on Random Networks","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2501.03162","title":"Deep-Relative-Trust-Based Diffusion for Decentralized Deep Learning","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2505.11307","title":"Diffusion Learning with Partial Agent Participation and Local Updates","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2508.20898","title":"CoCoL: A Communication Efficient Decentralized Collaborative Method for Multi-Robot Systems","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.18129","title":"Pareto-optimal Trade-offs Between Communication and Computation with Flexible Gradient Tracking","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.18213","title":"Joint Cooperative and Non-Cooperative Localization in WSNs with Distributed Scaled Proximal ADMM Algorithms","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2512.01732","title":"Beyond Scaffold: A Unified Spatio-Temporal Gradient Tracking Method","created":"2025-12-01","cited_by_count":0,"area":null}],"next_cursor":"100"}