{"total":229,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141,"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":"2206.08307","title":"Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning","created":"2022-06-16","cited_by_count":79,"area":null},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59,"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":"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":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"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":"2208.10888","title":"Joint Privacy Enhancement and Quantization in Federated Learning","created":"2022-08-23","cited_by_count":35,"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":"2110.03300","title":"Permutation Compressors for Provably Faster Distributed Nonconvex Optimization","created":"2021-10-07","cited_by_count":32,"area":null},{"id":"2103.11109","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2305.15155","title":"Momentum Provably Improves Error Feedback!","created":"2023-05-24","cited_by_count":31,"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":"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":"2201.07598","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","created":"2022-01-19","cited_by_count":23,"area":null},{"id":"2201.11066","title":"Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization","created":"2022-01-26","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":"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":"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":"2303.02430","title":"CFlowNets: Continuous Control with Generative Flow Networks","created":"2023-03-04","cited_by_count":19,"area":"diffusion"},{"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":"2210.16402","title":"GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity","created":"2022-10-28","cited_by_count":18,"area":null},{"id":"2304.08322","title":"Decentralized Learning Made Easy with DecentralizePy","created":"2023-04-17","cited_by_count":18,"area":null},{"id":"2103.02351","title":"Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates","created":"2021-03-03","cited_by_count":17,"area":null},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","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":"2205.04180","title":"EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization","created":"2022-05-09","cited_by_count":17,"area":null},{"id":"2306.14853","title":"Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles","created":"2023-06-26","cited_by_count":17,"area":null},{"id":"2105.07806","title":"Towards Demystifying Serverless Machine Learning Training","created":"2021-05-17","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":"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":"2110.03681","title":"Neural Tangent Kernel Empowered Federated Learning","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2111.01847","title":"Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning","created":"2021-11-02","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":"2403.06664","title":"Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System","created":"2024-03-11","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":"2203.15260","title":"Efficient Convex Optimization Requires Superlinear Memory","created":"2022-03-29","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":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","cited_by_count":13,"area":null},{"id":"2205.03914","title":"Federated Random Reshuffling with Compression and Variance Reduction","created":"2022-05-08","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":"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":"2206.03588","title":"Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation","created":"2022-06-07","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":"2305.18929","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":"2105.04153","title":"Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updates","created":"2021-05-10","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":"2205.15614","title":"Communication-Efficient Distributionally Robust Decentralized Learning","created":"2022-05-31","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":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2106.03524","title":"Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques","created":"2021-06-07","cited_by_count":9,"area":null},{"id":"2202.02491","title":"Distributed Learning With Sparsified Gradient Differences","created":"2022-02-05","cited_by_count":9,"area":null},{"id":"2203.01198","title":"Linear Stochastic Bandits over a Bit-Constrained Channel","created":"2022-03-02","cited_by_count":9,"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":"2305.05933","title":"Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2305.09896","title":"Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2404.09536","title":"Noiseless Privacy-Preserving Decentralized Learning","created":"2024-04-15","cited_by_count":9,"area":null},{"id":"2102.07214","title":"Communication-Efficient Distributed Optimization with Quantized Preconditioners","created":"2021-02-14","cited_by_count":8,"area":null},{"id":"2110.04350","title":"FRL: Federated Rank Learning","created":"2021-10-08","cited_by_count":8,"area":null},{"id":"2209.01346","title":"HammingMesh: A Network Topology for Large-Scale Deep Learning","created":"2022-09-03","cited_by_count":8,"area":null},{"id":"2210.07376","title":"ScionFL: Efficient and Robust Secure Quantized Aggregation","created":"2022-10-13","cited_by_count":8,"area":null},{"id":"2301.08897","title":"ScaDLES: Scalable Deep Learning over Streaming data at the Edge","created":"2023-01-21","cited_by_count":8,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2312.12863","title":"Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization","created":"2023-12-20","cited_by_count":8,"area":null},{"id":"2110.07751","title":"Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation","created":"2021-10-14","cited_by_count":7,"area":null},{"id":"2205.13341","title":"QUIC-FL: Quick Unbiased Compression for Federated Learning","created":"2022-05-26","cited_by_count":7,"area":null},{"id":"2302.07615","title":"Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2302.11466","title":"Advancements in Federated Learning: Models, Methods, and Privacy","created":"2023-02-22","cited_by_count":7,"area":null},{"id":"2304.09876","title":"Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing","created":"2023-04-19","cited_by_count":7,"area":null},{"id":"2307.07950","title":"Accelerating Distributed ML Training via Selective Synchronization","created":"2023-07-16","cited_by_count":7,"area":null},{"id":"2106.00564","title":"Wireless Federated Learning with Limited Communication and Differential Privacy","created":"2021-06-01","cited_by_count":6,"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":"2206.10452","title":"Shifted Compression Framework: Generalizations and Improvements","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2208.07237","title":"Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation","created":"2022-08-15","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}],"next_cursor":"100"}