{"total":45,"rows":[{"id":"2110.04175","title":"RelaySum for Decentralized Deep Learning on Heterogeneous Data","created":"2021-10-08","cited_by_count":39,"area":null},{"id":"2106.04469","title":"Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks","created":"2021-06-08","cited_by_count":19,"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":"2102.09234","title":"ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks","created":"2021-02-18","cited_by_count":13,"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":"2106.07243","title":"Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks","created":"2021-06-14","cited_by_count":12,"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":"2209.07116","title":"On Generalization of Decentralized Learning with Separable Data","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2112.15287","title":"Distributed Random Reshuffling over Networks","created":"2021-12-31","cited_by_count":7,"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":"2311.07939","title":"Discretized Distributed Optimization over Dynamic Digraphs","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2206.07944","title":"Distributed Online Private Learning of Convex Nondecomposable Objectives","created":"2022-06-16","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":"2307.11617","title":"Robust Fully-Asynchronous Methods for Distributed Training over General Architecture","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2308.05292","title":"Byzantine-Robust Decentralized Stochastic Optimization with Stochastic Gradient Noise-Independent Learning Error","created":"2023-08-10","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":"2402.18018","title":"Communication Efficient ConFederated Learning: An Event-Triggered SAGA Approach","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2403.00157","title":"Privacy-Preserving Distributed Optimization and Learning","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2502.10784","title":"Preconditioned Inexact Stochastic ADMM for Deep Model","created":"2025-02-15","cited_by_count":2,"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":"2205.14452","title":"Stochastic Gradient Methods with Compressed Communication for Decentralized Saddle Point Problems","created":"2022-05-28","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":"2310.00638","title":"A primal-dual perspective for distributed TD-learning","created":"2023-10-01","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":"2201.12488","title":"Achieving Efficient Distributed Machine Learning Using a Novel Non-Linear Class of Aggregation Functions","created":"2022-01-29","cited_by_count":0,"area":null},{"id":"2207.07543","title":"Pick your Neighbor: Local Gauss-Southwell Rule for Fast Asynchronous Decentralized Optimization","created":"2022-07-15","cited_by_count":0,"area":null},{"id":"2211.12640","title":"Resource-Constrained Decentralized Federated Learning via Personalized Event-Triggering","created":"2022-11-23","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":"2407.16728","title":"Distributed Difference of Convex Optimization","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2501.04409","title":"Lossless Privacy-Preserving Aggregation for Decentralized Federated Learning","created":"2025-01-08","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":"2505.10322","title":"Asynchronous Decentralized SGD under Non-Convexity: A Block-Coordinate Descent Framework","created":"2025-05-15","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":"2508.14565","title":"Cooperative SGD with Dynamic Mixing Matrices","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2508.20645","title":"A Hybrid Stochastic Gradient Tracking Method for Distributed Online Optimization Over Time-Varying Directed Networks","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":"2509.18134","title":"A Weighted Gradient Tracking Privacy-Preserving Method for Distributed Optimization","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2601.03442","title":"Local Updates in Distributed Optimization: Provable Acceleration and Topology Effects","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.03566","title":"Provably Convergent Decentralized Optimization over Directed Graphs under Generalized Smoothness","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2602.00791","title":"Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.20567","title":"Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2604.00449","title":"Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.19518","title":"Accelerating Optimization and Machine Learning through Decentralization","created":"2026-04-21","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}],"next_cursor":null}