{"total":68,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190,"area":null},{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123,"area":null},{"id":"2206.08307","title":"Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning","created":"2022-06-16","cited_by_count":79,"area":null},{"id":"2002.04013","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","created":"2020-02-10","cited_by_count":43,"area":"moe"},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2106.02743","title":"SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2203.13789","title":"FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations","created":"2022-03-25","cited_by_count":27,"area":null},{"id":"2110.08133","title":"Trade-offs of Local SGD at Scale: An Empirical Study","created":"2021-10-15","cited_by_count":20,"area":null},{"id":"2205.13797","title":"AsyncFedED: Asynchronous Federated Learning with Euclidean Distance based Adaptive Weight Aggregation","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2302.01463","title":"Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy","created":"2023-02-02","cited_by_count":18,"area":null},{"id":"2501.16168","title":"Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity","created":"2025-01-27","cited_by_count":18,"area":null},{"id":"2401.16265","title":"CO2: Efficient Distributed Training with Full Communication-Computation Overlap","created":"2024-01-29","cited_by_count":17,"area":null},{"id":"2305.13854","title":"The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2202.00955","title":"Asynchronous Decentralized Learning over Unreliable Wireless Networks","created":"2022-02-02","cited_by_count":13,"area":null},{"id":"2305.12213","title":"Taming Resource Heterogeneity In Distributed ML Training With Dynamic Batching","created":"2023-05-20","cited_by_count":12,"area":null},{"id":"2307.07652","title":"DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates","created":"2023-07-14","cited_by_count":12,"area":null},{"id":"2104.13130","title":"Secure and Efficient Federated Learning Through Layering and Sharding Blockchain","created":"2021-04-27","cited_by_count":10,"area":null},{"id":"2203.01214","title":"Towards Efficient and Stable K-Asynchronous Federated Learning with Unbounded Stale Gradients on Non-IID Data","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2103.01206","title":"Gradient Coding with Dynamic Clustering for Straggler-Tolerant Distributed Learning","created":"2021-03-01","cited_by_count":8,"area":null},{"id":"2106.12261","title":"Learning Under Delayed Feedback: Implicitly Adapting to Gradient Delays","created":"2021-06-23","cited_by_count":7,"area":null},{"id":"2402.11198","title":"Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients","created":"2024-02-17","cited_by_count":7,"area":null},{"id":"2402.11800","title":"Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling","created":"2024-02-19","cited_by_count":7,"area":"deeprl"},{"id":"2410.04285","title":"MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times","created":"2024-10-05","cited_by_count":6,"area":null},{"id":"2103.13026","title":"The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication","created":"2021-03-24","cited_by_count":5,"area":null},{"id":"2405.15545","title":"Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2407.19234","title":"Ordered Momentum for Asynchronous SGD","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2502.00775","title":"ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning","created":"2025-02-02","cited_by_count":5,"area":null},{"id":"2509.22860","title":"Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2104.05588","title":"Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)","created":"2021-04-12","cited_by_count":4,"area":null},{"id":"2109.15226","title":"Coding for Straggler Mitigation in Federated Learning","created":"2021-09-30","cited_by_count":4,"area":null},{"id":"2204.06240","title":"CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPU","created":"2022-04-13","cited_by_count":4,"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":"2104.08364","title":"Sync-Switch: Hybrid Parameter Synchronization for Distributed Deep Learning","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2402.09247","title":"Momentum Approximation in Asynchronous Private Federated Learning","created":"2024-02-14","cited_by_count":3,"area":null},{"id":"2406.00302","title":"FedAST: Federated Asynchronous Simultaneous Training","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2208.03134","title":"Adaptive Stochastic Gradient Descent for Fast and Communication-Efficient Distributed Learning","created":"2022-08-04","cited_by_count":2,"area":null},{"id":"2210.03521","title":"STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronization","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2211.00889","title":"Accelerating Parallel Stochastic Gradient Descent via Non-blocking Mini-batches","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2401.01728","title":"Ravnest: Decentralized Asynchronous Training on Heterogeneous Devices","created":"2024-01-03","cited_by_count":2,"area":null},{"id":"2405.10123","title":"Asynchronous Federated Stochastic Optimization for Heterogeneous Objectives Under Arbitrary Delays","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2502.08206","title":"Optimizing Asynchronous Federated Learning: A Delicate Trade-Off Between Model-Parameter Staleness and Update Frequency","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2508.01675","title":"Asynchronous Federated Learning with non-convex client objective functions and heterogeneous dataset","created":"2025-08-03","cited_by_count":2,"area":null},{"id":"2601.19379","title":"Optimal Asynchronous Stochastic Nonconvex Optimization under Heavy-Tailed Noise","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2605.13434","title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.18174","title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2607.01083","title":"Staleness-Learning Rate Scaling Laws for Asynchronous RLHF","created":"2026-07-01","cited_by_count":2,"area":"alignment"},{"id":"2111.14955","title":"Privacy-Preserving Serverless Edge Learning with Decentralized Small Data","created":"2021-11-29","cited_by_count":1,"area":null},{"id":"2201.12990","title":"Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2212.11805","title":"BSAC-CoEx: Coexistence of URLLC and Distributed Learning Services via Device Selection","created":"2022-12-22","cited_by_count":1,"area":null},{"id":"2404.09679","title":"AntDT: A Self-Adaptive Distributed Training Framework for Leader and Straggler Nodes","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2405.16966","title":"Dual-Delayed Asynchronous SGD for Arbitrarily Heterogeneous Data","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2405.20988","title":"Communication-Efficient Distributed Deep Learning via Federated Dynamic Averaging","created":"2024-05-31","cited_by_count":1,"area":null},{"id":"2406.11159","title":"Distributed Stochastic Gradient Descent with Staleness: A Stochastic Delay Differential Equation Based Framework","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2408.07503","title":"Faster Stochastic Optimization with Arbitrary Delays via Asynchronous Mini-Batching","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2502.15940","title":"Orthogonal Calibration for Asynchronous Federated Learning","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2505.23973","title":"Adaptive Deadline and Batch Layered Synchronized Federated Learning","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2110.08941","title":"Distributed Optimization using Heterogeneous Compute Systems","created":"2021-10-03","cited_by_count":0,"area":null},{"id":"2202.08302","title":"Cost-Efficient Distributed Learning via Combinatorial Multi-Armed Bandits","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2202.09019","title":"Distributed Multi-Agent Reinforcement Learning with One-hop Neighbors and Compute Straggler Mitigation","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2204.02632","title":"DeFTA: A Plug-and-Play Decentralized Replacement for FedAvg","created":"2022-04-06","cited_by_count":0,"area":null},{"id":"2304.08589","title":"Fast and Straggler-Tolerant Distributed SGD with Reduced Computation Load","created":"2023-04-17","cited_by_count":0,"area":null},{"id":"2406.03516","title":"Buffered Asynchronous Secure Aggregation for Cross-Device Federated Learning","created":"2024-06-05","cited_by_count":0,"area":null},{"id":"2506.03746","title":"Dropout-Robust Mechanisms for Differentially Private and Fully Decentralized Mean Estimation","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2511.00655","title":"Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning","created":"2025-11-01","cited_by_count":0,"area":"distill"},{"id":"2602.03802","title":"Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2605.14373","title":"Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.20739","title":"Pipelined Gradient Coding","created":"2026-07-22","cited_by_count":0,"area":null}],"next_cursor":null}