{"total":304,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172,"area":null},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136,"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":"2104.02151","title":"Distributed Learning in Wireless Networks: Recent Progress and Future Challenges","created":"2021-04-05","cited_by_count":129,"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":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115,"area":null},{"id":"2308.08165","title":"Stochastic Controlled Averaging for Federated Learning with Communication Compression","created":"2023-08-16","cited_by_count":101,"area":null},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88,"area":null},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86,"area":null},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78,"area":null},{"id":"2301.09604","title":"FedExP: Speeding Up Federated Averaging via Extrapolation","created":"2023-01-23","cited_by_count":69,"area":null},{"id":"2104.14362","title":"From Distributed Machine Learning to Federated Learning: A Survey","created":"2021-04-29","cited_by_count":66,"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":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2108.08842","title":"EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning","created":"2021-08-19","cited_by_count":55,"area":null},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55,"area":null},{"id":"2105.08339","title":"DRIVE: One-bit Distributed Mean Estimation","created":"2021-05-18","cited_by_count":52,"area":null},{"id":"2106.02969","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","created":"2021-06-05","cited_by_count":52,"area":null},{"id":"2410.13849","title":"From Gradient Clipping to Normalization for Heavy Tailed SGD","created":"2024-10-17","cited_by_count":49,"area":null},{"id":"2112.06274","title":"SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification","created":"2021-12-12","cited_by_count":46,"area":null},{"id":"2108.00951","title":"Rethinking gradient sparsification as total error minimization","created":"2021-08-02","cited_by_count":41,"area":null},{"id":"2201.13320","title":"BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression","created":"2022-01-31","cited_by_count":41,"area":null},{"id":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41,"area":null},{"id":"2206.07284","title":"A Survey on Gradient Inversion: Attacks, Defenses and Future Directions","created":"2022-06-15","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":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2202.07262","title":"Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods","created":"2022-02-15","cited_by_count":37,"area":null},{"id":"2103.03239","title":"Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices","created":"2021-03-04","cited_by_count":36,"area":null},{"id":"2206.08330","title":"Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data","created":"2022-06-16","cited_by_count":36,"area":null},{"id":"2208.10888","title":"Joint Privacy Enhancement and Quantization in Federated Learning","created":"2022-08-23","cited_by_count":35,"area":null},{"id":"2206.09888","title":"SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression","created":"2022-06-20","cited_by_count":34,"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":"2101.10761","title":"An Efficient Statistical-based Gradient Compression Technique for Distributed Training Systems","created":"2021-01-26","cited_by_count":32,"area":null},{"id":"2106.11879","title":"Asynchronous Stochastic Optimization Robust to Arbitrary Delays","created":"2021-06-22","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":"2109.05872","title":"Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering","created":"2021-09-13","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":"2305.12475","title":"Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods","created":"2023-05-21","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":"2204.13169","title":"FedShuffle: Recipes for Better Use of Local Work in Federated Learning","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2103.08870","title":"Learned Gradient Compression for Distributed Deep Learning","created":"2021-03-16","cited_by_count":20,"area":null},{"id":"2106.08882","title":"Robust Training in High Dimensions via Block Coordinate Geometric Median Descent","created":"2021-06-16","cited_by_count":20,"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":"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":"2205.05632","title":"On Distributed Adaptive Optimization with Gradient Compression","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2405.15593","title":"MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence","created":"2024-05-24","cited_by_count":19,"area":null},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2111.00556","title":"Revealing and Protecting Labels in Distributed Training","created":"2021-10-31","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":"2202.00280","title":"Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?","created":"2022-02-01","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":"2107.11304","title":"Finite-Bit Quantization For Distributed Algorithms With Linear Convergence","created":"2021-07-23","cited_by_count":15,"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":"2302.08545","title":"THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression","created":"2023-02-16","cited_by_count":15,"area":null},{"id":"2311.05645","title":"EControl: Fast Distributed Optimization with Compression and Error Control","created":"2023-11-06","cited_by_count":15,"area":null},{"id":"2112.13097","title":"Faster Rates for Compressed Federated Learning with Client-Variance Reduction","created":"2021-12-24","cited_by_count":14,"area":null},{"id":"2210.14664","title":"Coresets for Vertical Federated Learning: Regularized Linear Regression and $K$-Means Clustering","created":"2022-10-26","cited_by_count":14,"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":"2311.14632","title":"Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach","created":"2023-11-24","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":"2102.09234","title":"ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks","created":"2021-02-18","cited_by_count":13,"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":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"area":null},{"id":"2406.00489","title":"Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction","created":"2024-06-01","cited_by_count":13,"area":null},{"id":"2502.07923","title":"Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under $(L_0, L_1)$-Smoothness","created":"2025-02-11","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":"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":"2301.00944","title":"Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning","created":"2023-01-03","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":"2506.01260","title":"Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2508.15706","title":"Overcoming the Communication-Performance Tradeoff in LLM Pretraining","created":"2025-08-21","cited_by_count":12,"area":null},{"id":"2102.07972","title":"Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approach","created":"2021-02-16","cited_by_count":11,"area":null},{"id":"2204.02321","title":"SAFARI: Sparsity enabled Federated Learning with Limited and Unreliable Communications","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2205.14473","title":"Efficient-Adam: Communication-Efficient Distributed Adam","created":"2022-05-28","cited_by_count":11,"area":null},{"id":"2206.03588","title":"Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2206.05558","title":"Communication-Efficient Robust Federated Learning with Noisy Labels","created":"2022-06-11","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":"2411.07724","title":"Convergence Rate Analysis of LION","created":"2024-11-12","cited_by_count":11,"area":null},{"id":"2411.10619","title":"Electrical Load Forecasting in Smart Grid: A Personalized Federated Learning Approach","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2411.19870","title":"DeMo: Decoupled Momentum Optimization","created":"2024-11-29","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":"2507.08784","title":"Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees","created":"2025-07-11","cited_by_count":11,"area":null},{"id":"2102.06025","title":"Large-Scale Training System for 100-Million Classification at Alibaba","created":"2021-02-09","cited_by_count":10,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"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":"2305.12201","title":"GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training","created":"2023-05-20","cited_by_count":10,"area":null},{"id":"2308.00263","title":"Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation","created":"2023-08-01","cited_by_count":10,"area":null},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2102.03970","title":"Coordinating Momenta for Cross-silo Federated Learning","created":"2021-02-08","cited_by_count":9,"area":null},{"id":"2102.08374","title":"IntSGD: Adaptive Floatless Compression of Stochastic Gradients","created":"2021-02-16","cited_by_count":9,"area":null},{"id":"2109.03999","title":"Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies","created":"2021-09-09","cited_by_count":9,"area":null}],"next_cursor":"100"}