{"total":376,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2101.11203","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","created":"2021-01-27","cited_by_count":193,"area":null},{"id":"2211.08413","title":"Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges","created":"2022-11-15","cited_by_count":138,"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":"2308.08165","title":"Stochastic Controlled Averaging for Federated Learning with Communication Compression","created":"2023-08-16","cited_by_count":101,"area":null},{"id":"2206.10341","title":"Neurotoxin: Durable Backdoors in Federated Learning","created":"2022-06-12","cited_by_count":98,"area":null},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75,"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":"2107.11621","title":"FedLab: A Flexible Federated Learning Framework","created":"2021-07-24","cited_by_count":55,"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":"2101.12704","title":"Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis","created":"2021-01-29","cited_by_count":51,"area":null},{"id":"2103.17150","title":"Federated Learning: A Signal Processing Perspective","created":"2021-03-31","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":"2204.10607","title":"Federated Learning via Inexact ADMM","created":"2022-04-22","cited_by_count":44,"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":"2305.16296","title":"A Guide Through the Zoo of Biased SGD","created":"2023-05-25","cited_by_count":40,"area":null},{"id":"2206.04055","title":"Gradient Obfuscation Gives a False Sense of Security in Federated Learning","created":"2022-06-08","cited_by_count":39,"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":"2110.10302","title":"Layer-wise Adaptive Model Aggregation for Scalable Federated Learning","created":"2021-10-19","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":"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":"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":"2412.06157","title":"Membership Inference Attacks and Defenses in Federated Learning: A Survey","created":"2024-12-09","cited_by_count":31,"area":"safety"},{"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":"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":"2106.00797","title":"QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning","created":"2021-06-01","cited_by_count":26,"area":null},{"id":"2101.05471","title":"Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration","created":"2021-01-14","cited_by_count":25,"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":"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":"2107.09461","title":"CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression","created":"2021-07-20","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":"2305.18469","title":"Reducing Communication for Split Learning by Randomized Top-k Sparsification","created":"2023-05-29","cited_by_count":22,"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":"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":"2106.04759","title":"Communication-efficient SGD: From Local SGD to One-Shot Averaging","created":"2021-06-09","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":"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":"2206.07021","title":"Federated Optimization Algorithms with Random Reshuffling and Gradient Compression","created":"2022-06-14","cited_by_count":18,"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":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18,"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":"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":"2102.01732","title":"Truly Sparse Neural Networks at Scale","created":"2021-02-02","cited_by_count":16,"area":null},{"id":"2106.08895","title":"Masked Training of Neural Networks with Partial Gradients","created":"2021-06-16","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":"2105.07320","title":"LocalNewton: Reducing Communication Bottleneck for Distributed Learning","created":"2021-05-16","cited_by_count":15,"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":"2112.06694","title":"Optimal Rate Adaption in Federated Learning with Compressed Communications","created":"2021-12-13","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":"2104.03490","title":"Joint Optimization of Communications and Federated Learning Over the Air","created":"2021-04-08","cited_by_count":14,"area":null},{"id":"2203.04925","title":"Correlated quantization for distributed mean estimation and optimization","created":"2022-03-09","cited_by_count":14,"area":null},{"id":"2302.03662","title":"Federated Learning with Regularized Client Participation","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","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":"2102.06329","title":"Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients","created":"2021-02-12","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":"2106.02797","title":"Neural Distributed Source Coding","created":"2021-06-05","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":"2405.15861","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2405.18972","title":"Federated Learning with Bilateral Curation for Partially Class-Disjoint Data","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2506.14562","title":"AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs","created":"2025-06-17","cited_by_count":13,"area":null},{"id":"2105.06697","title":"Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence","created":"2021-05-14","cited_by_count":12,"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":"2301.02654","title":"Does compressing activations help model parallel training?","created":"2023-01-06","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":"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":"2103.16055","title":"1-Bit Compressive Sensing for Efficient Federated Learning Over the Air","created":"2021-03-30","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":"2210.14396","title":"FeDXL: Provable Federated Learning for Deep X-Risk Optimization","created":"2022-10-26","cited_by_count":11,"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":"2305.17581","title":"Knowledge Distillation Performs Partial Variance Reduction","created":"2023-05-27","cited_by_count":11,"area":"distill"},{"id":"2305.18929","title":"Clip21: Error Feedback for Gradient Clipping","created":"2023-05-30","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":"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":"2105.04153","title":"Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updates","created":"2021-05-10","cited_by_count":10,"area":null}],"next_cursor":"100"}