{"total":51,"rows":[{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56,"area":null},{"id":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40,"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":"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":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17,"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":"2105.06697","title":"Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence","created":"2021-05-14","cited_by_count":12,"area":null},{"id":"2106.07243","title":"Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks","created":"2021-06-14","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":"2210.13767","title":"Networked Signal and Information Processing","created":"2022-10-25","cited_by_count":10,"area":null},{"id":"2301.05872","title":"CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence","created":"2023-01-14","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":"2108.04448","title":"Decentralized Composite Optimization with Compression","created":"2021-08-10","cited_by_count":7,"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":"2503.20117","title":"Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2209.01850","title":"DISA: A Dual Inexact Splitting Algorithm for Distributed Convex Composite Optimization","created":"2022-09-05","cited_by_count":5,"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":"2202.05498","title":"Fast and Robust Sparsity Learning over Networks: A Decentralized Surrogate Median Regression Approach","created":"2022-02-11","cited_by_count":4,"area":null},{"id":"2301.12677","title":"Distributed Stochastic Optimization under a General Variance Condition","created":"2023-01-30","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":"2403.17572","title":"Enhancing Privacy in Federated Learning through Local Training","created":"2024-03-26","cited_by_count":3,"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":"2306.12037","title":"Distributed Random Reshuffling Methods with Improved Convergence","created":"2023-06-21","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":"2104.01555","title":"Decentralized Statistical Inference with Unrolled Graph Neural Networks","created":"2021-04-04","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":"2303.09611","title":"Decentralized Riemannian natural gradient methods with Kronecker-product approximations","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2306.06375","title":"Optimized Gradient Tracking for Decentralized Online Learning","created":"2023-06-10","cited_by_count":1,"area":null},{"id":"2310.07983","title":"Achieving Linear Speedup with ProxSkip in Distributed Stochastic Optimization","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2402.02356","title":"Decentralized Sum-of-Nonconvex Optimization","created":"2024-02-04","cited_by_count":1,"area":null},{"id":"2405.18031","title":"Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2503.15804","title":"Communication Efficient Federated Learning with Linear Convergence on Heterogeneous Data","created":"2025-03-20","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":"2601.07021","title":"Tight Analysis of Decentralized SGD: A Markov Chain Perspective","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2603.01730","title":"Decentralized Federated Learning by Partial Message Exchange","created":"2026-03-02","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":"2403.02589","title":"MUSIC: Accelerated Convergence for Distributed Optimization With Inexact and Exact Methods","created":"2024-03-05","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":"2503.07563","title":"Efficient Distributed Learning over Decentralized Networks with Convoluted Support Vector Machine","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2503.16123","title":"Distributed Learning over Arbitrary Topology: Linear Speed-Up with Polynomial Transient Time","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2510.23362","title":"Robust Non-negative Proximal Gradient Algorithm for Inverse Problems","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2512.02852","title":"Adaptive Decentralized Federated Learning for Robust Optimization","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.16148","title":"Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication acceleration","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2605.00281","title":"High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking","created":"2026-04-30","cited_by_count":0,"area":null}],"next_cursor":null}