{"total":99,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"area":null},{"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":"2305.16296","title":"A Guide Through the Zoo of Biased SGD","created":"2023-05-25","cited_by_count":40,"area":null},{"id":"2303.10837","title":"FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System","created":"2023-03-20","cited_by_count":38,"area":null},{"id":"2103.02051","title":"Cross-Gradient Aggregation for Decentralized Learning from Non-IID data","created":"2021-03-02","cited_by_count":33,"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":"2110.03300","title":"Permutation Compressors for Provably Faster Distributed Nonconvex Optimization","created":"2021-10-07","cited_by_count":32,"area":null},{"id":"2305.15155","title":"Momentum Provably Improves Error Feedback!","created":"2023-05-24","cited_by_count":31,"area":null},{"id":"2205.06730","title":"Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints","created":"2022-05-13","cited_by_count":30,"area":null},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30,"area":null},{"id":"2302.00543","title":"DoCoFL: Downlink Compression for Cross-Device Federated Learning","created":"2023-02-01","cited_by_count":28,"area":null},{"id":"2110.05323","title":"ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training","created":"2021-10-11","cited_by_count":27,"area":null},{"id":"2202.00998","title":"3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation","created":"2022-02-02","cited_by_count":27,"area":null},{"id":"2101.08837","title":"Time-Correlated Sparsification for Communication-Efficient Federated Learning","created":"2021-01-21","cited_by_count":26,"area":null},{"id":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26,"area":null},{"id":"2102.07158","title":"Distributed Second Order Methods with Fast Rates and Compressed Communication","created":"2021-02-14","cited_by_count":25,"area":null},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25,"area":null},{"id":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24,"area":null},{"id":"2111.05326","title":"The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning","created":"2021-11-09","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":"2104.11125","title":"ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training","created":"2021-04-21","cited_by_count":22,"area":null},{"id":"2102.07245","title":"Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization","created":"2021-02-14","cited_by_count":21,"area":null},{"id":"2102.12528","title":"Preserved central model for faster bidirectional compression in distributed settings","created":"2021-02-24","cited_by_count":21,"area":null},{"id":"2207.03957","title":"Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox","created":"2022-07-08","cited_by_count":19,"area":null},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17,"area":null},{"id":"2109.03194","title":"On the Convergence of Decentralized Adaptive Gradient Methods","created":"2021-09-07","cited_by_count":17,"area":null},{"id":"2111.05897","title":"Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2302.02589","title":"$z$-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning","created":"2023-02-06","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":"2211.00188","title":"Adaptive Compression for Communication-Efficient Distributed Training","created":"2022-10-31","cited_by_count":16,"area":null},{"id":"2110.03313","title":"Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2202.06009","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","created":"2022-02-12","cited_by_count":15,"area":null},{"id":"2104.03490","title":"Joint Optimization of Communications and Federated Learning Over the Air","created":"2021-04-08","cited_by_count":14,"area":null},{"id":"2106.03056","title":"MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization","created":"2021-06-06","cited_by_count":14,"area":null},{"id":"2410.15526","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","created":"2024-10-20","cited_by_count":14,"area":null},{"id":"2104.06685","title":"BROADCAST: Reducing Both Stochastic and Compression Noise to Robustify Communication-Efficient Federated Learning","created":"2021-04-14","cited_by_count":13,"area":null},{"id":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","cited_by_count":13,"area":null},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","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":"2111.00705","title":"Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization","created":"2021-11-01","cited_by_count":12,"area":null},{"id":"2212.08496","title":"Federated Learning with Flexible Control","created":"2022-12-16","cited_by_count":12,"area":null},{"id":"2310.09804","title":"Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates","created":"2023-10-15","cited_by_count":12,"area":null},{"id":"2305.07612","title":"Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2305.18929","title":"Clip21: Error Feedback for Gradient Clipping","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2302.11147","title":"Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning","created":"2023-02-22","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":"2101.02198","title":"Federated Learning over Noisy Channels: Convergence Analysis and Design Examples","created":"2021-01-06","cited_by_count":8,"area":null},{"id":"2110.03294","title":"EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2206.09446","title":"Compression and Data Similarity: Combination of Two Techniques for Communication-Efficient Solving of Distributed Variational Inequalities","created":"2022-06-19","cited_by_count":8,"area":null},{"id":"2306.03240","title":"Improving Accelerated Federated Learning with Compression and Importance Sampling","created":"2023-06-05","cited_by_count":8,"area":null},{"id":"2108.04448","title":"Decentralized Composite Optimization with Compression","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2212.01523","title":"GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning","created":"2022-12-03","cited_by_count":7,"area":null},{"id":"2301.08869","title":"A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2410.12707","title":"FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression","created":"2024-10-16","cited_by_count":7,"area":null},{"id":"2202.00255","title":"DoCoM: Compressed Decentralized Optimization with Near-Optimal Sample Complexity","created":"2022-02-01","cited_by_count":6,"area":null},{"id":"2209.05148","title":"Personalized Federated Learning with Communication Compression","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2312.07060","title":"Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learning","created":"2023-12-12","cited_by_count":6,"area":null},{"id":"2407.04480","title":"LoCo: Low-Bit Communication Adaptor for Large-scale Model Training","created":"2024-07-05","cited_by_count":6,"area":null},{"id":"2111.02083","title":"Federated Expectation Maximization with heterogeneity mitigation and variance reduction","created":"2021-11-03","cited_by_count":5,"area":null},{"id":"2304.07460","title":"Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacy","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2112.05559","title":"Collaborative Learning over Wireless Networks: An Introductory Overview","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2203.02383","title":"Distributed Methods with Absolute Compression and Error Compensation","created":"2022-03-04","cited_by_count":4,"area":null},{"id":"2207.12779","title":"Reconciling Security and Communication Efficiency in Federated Learning","created":"2022-07-26","cited_by_count":4,"area":null},{"id":"2303.05206","title":"FedREP: A Byzantine-Robust, Communication-Efficient and Privacy-Preserving Framework for Federated Learning","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2304.13545","title":"Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2307.07406","title":"Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noise","created":"2023-07-14","cited_by_count":4,"area":null},{"id":"2410.16871","title":"Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2107.03510","title":"Federated Learning with Downlink Device Selection","created":"2021-07-07","cited_by_count":3,"area":null},{"id":"2305.04279","title":"Boosting Distributed Machine Learning Training Through Loss-tolerant Transmission Protocol","created":"2023-05-07","cited_by_count":3,"area":null},{"id":"2502.13482","title":"Smoothed Normalization for Efficient Distributed Private Optimization","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2109.08346","title":"Comfetch: Federated Learning of Large Networks on Constrained Clients via Sketching","created":"2021-09-17","cited_by_count":2,"area":null},{"id":"2110.07649","title":"Federated learning and next generation wireless communications: A survey on bidirectional relationship","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2203.06798","title":"The Role of Local Steps in Local SGD","created":"2022-03-14","cited_by_count":2,"area":null},{"id":"2206.00529","title":"Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top","created":"2022-06-01","cited_by_count":2,"area":null},{"id":"2302.09634","title":"Magnitude Matters: Fixing SIGNSGD Through Magnitude-Aware Sparsification in the Presence of Data Heterogeneity","created":"2023-02-19","cited_by_count":2,"area":null},{"id":"2402.11857","title":"Communication-Efficient Distributed Learning with Local Immediate Error Compensation","created":"2024-02-19","cited_by_count":2,"area":null},{"id":"2403.02347","title":"On the Convergence of Federated Learning Algorithms without Data Similarity","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2411.03730","title":"NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2508.04950","title":"Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2511.14501","title":"Improved Convergence in Parameter-Agnostic Error Feedback through Momentum","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2309.13307","title":"CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2405.06636","title":"Federated Document Visual Question Answering: A Pilot Study","created":"2024-05-10","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":"2412.17082","title":"MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes","created":"2024-12-22","cited_by_count":1,"area":null},{"id":"2506.05271","title":"Tight analyses of first-order methods with error feedback","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2604.24012","title":"FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection","created":"2026-04-27","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":"2103.07974","title":"CrossoverScheduler: Overlapping Multiple Distributed Training Applications in a Crossover Manner","created":"2021-03-14","cited_by_count":0,"area":null},{"id":"2109.12497","title":"Unbiased Single-scale and Multi-scale Quantizers for Distributed Optimization","created":"2021-09-26","cited_by_count":0,"area":null},{"id":"2208.05631","title":"Quantized Adaptive Subgradient Algorithms and Their Applications","created":"2022-08-11","cited_by_count":0,"area":null},{"id":"2209.15203","title":"Downlink Compression Improves TopK Sparsification","created":"2022-09-30","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":"2404.02779","title":"Federated Computing -- Survey on Building Blocks, Extensions and Systems","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2511.05593","title":"Gradient Projection onto Historical Descent Directions for Communication-Efficient Federated Learning","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2607.29674","title":"Sign compression for Muon: SignMuon, MuonSign, and the Limits of Error Feedback","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}