{"total":66,"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":"2206.03665","title":"Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression","created":"2022-06-08","cited_by_count":33,"area":null},{"id":"2204.04452","title":"Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data","created":"2022-04-09","cited_by_count":32,"area":null},{"id":"2301.01313","title":"Decentralized Gradient Tracking with Local Steps","created":"2023-01-03","cited_by_count":32,"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":"2210.04757","title":"On the Performance of Gradient Tracking with Local Updates","created":"2022-10-10","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":"2305.16297","title":"Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2204.06477","title":"Data-heterogeneity-aware Mixing for Decentralized Learning","created":"2022-04-13","cited_by_count":12,"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":"2208.00779","title":"DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization","created":"2022-07-26","cited_by_count":8,"area":null},{"id":"2209.07116","title":"On Generalization of Decentralized Learning with Separable Data","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2402.07471","title":"Differentially Private Decentralized Learning with Random Walks","created":"2024-02-12","cited_by_count":8,"area":null},{"id":"2405.00965","title":"Robust Decentralized Learning with Local Updates and Gradient Tracking","created":"2024-05-02","cited_by_count":8,"area":null},{"id":"2306.08289","title":"$\\textbf{A}^2\\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2405.20114","title":"Towards Faster Decentralized Stochastic Optimization with Communication Compression","created":"2024-05-30","cited_by_count":5,"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":"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":"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":"2306.07159","title":"On the Computation-Communication Trade-Off with A Flexible Gradient Tracking Approach","created":"2023-06-12","cited_by_count":4,"area":null},{"id":"2409.17189","title":"Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2501.15259","title":"Scalable Decentralized Learning with Teleportation","created":"2025-01-25","cited_by_count":3,"area":null},{"id":"2306.12037","title":"Distributed Random Reshuffling Methods with Improved Convergence","created":"2023-06-21","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":"2310.16105","title":"Locally Differentially Private Gradient Tracking for Distributed Online Learning over Directed Graphs","created":"2023-10-24","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":"2502.02727","title":"Gradient Correction in Federated Learning with Adaptive Optimization","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2601.21624","title":"Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps","created":"2026-01-29","cited_by_count":2,"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":"2206.04113","title":"Push--Pull with Device Sampling","created":"2022-06-08","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":"2310.07983","title":"Achieving Linear Speedup with ProxSkip in Distributed Stochastic Optimization","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2403.03292","title":"Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data","created":"2024-03-05","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":"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":"2601.07021","title":"Tight Analysis of Decentralized SGD: A Markov Chain Perspective","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2601.11435","title":"Near-Optimal Decentralized Stochastic Nonconvex Optimization with Heavy-Tailed Noise","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2604.25467","title":"Subspace Optimization for Efficient Federated Learning under Heterogeneous Data","created":"2026-04-28","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":"2212.08743","title":"Addressing Data Heterogeneity in Decentralized Learning via Topological Pre-processing","created":"2022-12-16","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":"2307.13430","title":"Achieving Linear Speedup in Decentralized Stochastic Compositional Minimax Optimization","created":"2023-07-25","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":"2310.15890","title":"Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2311.05760","title":"Compressed and Sparse Models for Non-Convex Decentralized Learning","created":"2023-11-09","cited_by_count":0,"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":"2403.18343","title":"The Artificial Neural Twin -- Process Optimization and Continual Learning in Distributed Process Chains","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2405.04566","title":"Fast Decentralized Gradient Tracking for Federated Minimax Optimization with Local Updates","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2405.13961","title":"SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2407.02689","title":"Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2409.19279","title":"Distributed Optimization via Energy Conservation Laws in Dilated Coordinates","created":"2024-09-28","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":"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":"2504.12742","title":"Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum","created":"2025-04-17","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":"2511.19513","title":"Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2602.03682","title":"Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2606.04757","title":"Near-Optimal Decentralized Stochastic Convex Optimization over Networks","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.25535","title":"Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.05789","title":"Dimension-Free Decentralized Nonsmooth Nonconvex Stochastic Optimization","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}