{"total":55,"rows":[{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38,"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":"2202.01545","title":"Byzantine-Robust Decentralized Learning via ClippedGossip","created":"2022-02-03","cited_by_count":31,"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":"2206.05091","title":"Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging","created":"2022-06-10","cited_by_count":27,"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":"2205.08443","title":"On the (In)security of Peer-to-Peer Decentralized Machine Learning","created":"2022-05-17","cited_by_count":23,"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":"2310.01972","title":"Epidemic Learning: Boosting Decentralized Learning with Randomized Communication","created":"2023-10-03","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":"2405.01031","title":"The Privacy Power of Correlated Noise in Decentralized Learning","created":"2024-05-02","cited_by_count":18,"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":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2312.10935","title":"AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devices","created":"2023-12-18","cited_by_count":15,"area":null},{"id":"2212.02724","title":"Decentralized Stochastic Gradient Descent Ascent for Finite-Sum Minimax Problems","created":"2022-12-06","cited_by_count":11,"area":null},{"id":"2306.02939","title":"Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm","created":"2023-06-05","cited_by_count":10,"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":"2310.20369","title":"Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm","created":"2023-10-31","cited_by_count":9,"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":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2205.06689","title":"Heavy-Tail Phenomenon in Decentralized SGD","created":"2022-05-13","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":"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":"2205.11048","title":"GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Model","created":"2022-05-23","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":"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":"2406.00621","title":"Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learning from Distributed Data","created":"2024-06-02","cited_by_count":4,"area":null},{"id":"2410.11998","title":"From promise to practice: realizing high-performance decentralized training","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2501.12344","title":"CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2301.02151","title":"Beyond spectral gap (extended): The role of the topology in decentralized learning","created":"2023-01-05","cited_by_count":3,"area":null},{"id":"2310.03461","title":"Towards Understanding Generalization and Stability Gaps between Centralized and Decentralized Federated Learning","created":"2023-10-05","cited_by_count":3,"area":null},{"id":"2406.20006","title":"On the Trade-off between Flatness and Optimization in Distributed Learning","created":"2024-06-28","cited_by_count":3,"area":null},{"id":"2412.01630","title":"Review of Mathematical Optimization in Federated Learning","created":"2024-12-02","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":"2306.03322","title":"Decentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate","created":"2023-06-06","cited_by_count":2,"area":null},{"id":"2507.06931","title":"DICE: Data Influence Cascade in Decentralized Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2602.03383","title":"Dynamic Topology Optimization for Non-IID Data in Decentralized Learning","created":"2026-02-03","cited_by_count":2,"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":"2406.02939","title":"Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2410.06482","title":"OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2411.00365","title":"ROSS: RObust decentralized Stochastic learning based on Shapley values","created":"2024-11-01","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":"2606.09154","title":"Improved Convergence Analysis of Topology Dependence in Decentralized SGD","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.11081","title":"Unifying Local Communications and Local Updates for LLM Pretraining","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2404.13669","title":"Rate Analysis of Coupled Distributed Stochastic Approximation for Misspecified Optimization","created":"2024-04-21","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":"2504.17471","title":"GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework","created":"2025-04-24","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":"2509.22174","title":"Efficiency Boost in Decentralized Optimization: Reimagining Neighborhood Aggregation with Minimal Overhead","created":"2025-09-26","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":"2512.01732","title":"Beyond Scaffold: A Unified Spatio-Temporal Gradient Tracking Method","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2602.02899","title":"Decentralized SGD with Controlled Disagreement Finds Flatter Minima","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2608.26453","title":"Distributed Training using an Intelligent Network","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}