{"total":133,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2102.06387","title":"The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation","created":"2021-02-12","cited_by_count":128,"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":"2102.11845","title":"Learning with User-Level Privacy","created":"2021-02-23","cited_by_count":72,"area":null},{"id":"2102.04487","title":"Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning","created":"2021-02-08","cited_by_count":63,"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":"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":"2105.08339","title":"DRIVE: One-bit Distributed Mean Estimation","created":"2021-05-18","cited_by_count":52,"area":null},{"id":"2203.03761","title":"The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning","created":"2022-03-07","cited_by_count":39,"area":null},{"id":"2505.14669","title":"Quartet: Native FP4 Training Can Be Optimal for Large Language Models","created":"2025-05-20","cited_by_count":39,"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":"2206.09888","title":"SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression","created":"2022-06-20","cited_by_count":34,"area":null},{"id":"2108.02117","title":"FedJAX: Federated learning simulation with JAX","created":"2021-08-04","cited_by_count":32,"area":null},{"id":"2209.15328","title":"Sparse Random Networks for Communication-Efficient Federated Learning","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2204.01273","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","created":"2022-04-04","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":"2202.01267","title":"FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stations","created":"2022-02-02","cited_by_count":28,"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":"2102.12099","title":"Lossless Compression of Efficient Private Local Randomizers","created":"2021-02-24","cited_by_count":27,"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":"2207.06343","title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2204.09715","title":"Scaling Language Model Size in Cross-Device Federated Learning","created":"2022-03-31","cited_by_count":25,"area":null},{"id":"2310.11028","title":"Matrix Compression via Randomized Low Rank and Low Precision Factorization","created":"2023-10-17","cited_by_count":25,"area":null},{"id":"2111.00092","title":"Optimal Compression of Locally Differentially Private Mechanisms","created":"2021-10-29","cited_by_count":22,"area":null},{"id":"2304.01541","title":"Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2410.22815","title":"Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients","created":"2024-10-30","cited_by_count":22,"area":null},{"id":"2502.05003","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","created":"2025-02-07","cited_by_count":22,"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":"2411.17525","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2601.22813","title":"Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation","created":"2026-01-30","cited_by_count":21,"area":null},{"id":"2110.02291","title":"FedDQ: Communication-Efficient Federated Learning with Descending Quantization","created":"2021-10-05","cited_by_count":20,"area":null},{"id":"2102.01375","title":"Applications of Federated Learning in Smart Cities: Recent Advances, Taxonomy, and Open Challenges","created":"2021-02-02","cited_by_count":17,"area":null},{"id":"2211.00188","title":"Adaptive Compression for Communication-Efficient Distributed Training","created":"2022-10-31","cited_by_count":16,"area":null},{"id":"2111.04986","title":"Unified Group Fairness on Federated Learning","created":"2021-11-09","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":"2201.11865","title":"FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients","created":"2022-01-28","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":"2110.02226","title":"Communication-Efficient Federated Learning with Binary Neural Networks","created":"2021-10-05","cited_by_count":14,"area":null},{"id":"2201.02664","title":"Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory","created":"2022-01-07","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":"2306.04444","title":"Fast Optimal Locally Private Mean Estimation via Random Projections","created":"2023-06-07","cited_by_count":14,"area":null},{"id":"2210.13111","title":"Federated Learning and Meta Learning: Approaches, Applications, and Directions","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2301.12195","title":"BAFFLE: A Baseline of Backpropagation-Free Federated Learning","created":"2023-01-28","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":"2208.04505","title":"Towards Energy-Aware Federated Learning on Battery-Powered Clients","created":"2022-08-09","cited_by_count":11,"area":null},{"id":"2210.01708","title":"Exploring Parameter-Efficient Fine-Tuning to Enable Foundation Models in Federated Learning","created":"2022-10-04","cited_by_count":11,"area":null},{"id":"2310.20682","title":"Compression with Exact Error Distribution for Federated Learning","created":"2023-10-31","cited_by_count":11,"area":null},{"id":"2104.02748","title":"Communication-Efficient Agnostic Federated Averaging","created":"2021-04-06","cited_by_count":10,"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":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2106.06075","title":"A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2206.01432","title":"On the Generalization of Wasserstein Robust Federated Learning","created":"2022-06-03","cited_by_count":9,"area":null},{"id":"2306.04924","title":"Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2309.07809","title":"Communication Efficient Private Federated Learning Using Dithering","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2509.00404","title":"Metis: Training LLMs with FP4 Quantization","created":"2025-08-30","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":"2109.05613","title":"Critical Learning Periods in Federated Learning","created":"2021-09-12","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":"2211.02212","title":"Distributed Linear Bandits under Communication Constraints","created":"2022-11-04","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":"2405.20782","title":"Universal Exact Compression of Differentially Private Mechanisms","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2110.02065","title":"SDR: Efficient Neural Re-ranking using Succinct Document Representation","created":"2021-10-03","cited_by_count":7,"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":"2510.17802","title":"Unbiased Gradient Low-Rank Projection","created":"2025-10-20","cited_by_count":7,"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},{"id":"2210.15025","title":"Addressing Heterogeneity in Federated Learning via Distributional Transformation","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2306.12625","title":"Adaptive Compression in Federated Learning via Side Information","created":"2023-06-22","cited_by_count":6,"area":null},{"id":"2405.10096","title":"The Effect of Quantization in Federated Learning: A R\\'enyi Differential Privacy Perspective","created":"2024-05-16","cited_by_count":6,"area":null},{"id":"2407.01378","title":"Beyond Throughput and Compression Ratios: Towards High End-to-end Utility of Gradient Compression","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2604.07796","title":"Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2102.07521","title":"Distributed Online Learning for Joint Regret with Communication Constraints","created":"2021-02-15","cited_by_count":5,"area":null},{"id":"2103.07578","title":"Efficient Randomized Subspace Embeddings for Distributed Optimization under a Communication Budget","created":"2021-03-13","cited_by_count":5,"area":null},{"id":"2208.06095","title":"A Fast Blockchain-based Federated Learning Framework with Compressed Communications","created":"2022-08-12","cited_by_count":5,"area":null},{"id":"2406.18156","title":"FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2509.21940","title":"Sequential 1-bit Mean Estimation with Near-Optimal Sample Complexity","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2403.14716","title":"Distributed Learning based on 1-Bit Gradient Coding in the Presence of Stragglers","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2405.02341","title":"Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2405.20431","title":"Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspective","created":"2024-05-30","cited_by_count":4,"area":null},{"id":"2109.05222","title":"Fundamental limits of over-the-air optimization: Are analog schemes optimal?","created":"2021-09-11","cited_by_count":3,"area":null},{"id":"2111.08277","title":"Wyner-Ziv Gradient Compression for Federated Learning","created":"2021-11-16","cited_by_count":3,"area":null},{"id":"2202.11490","title":"Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2302.09624","title":"Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy","created":"2023-02-19","cited_by_count":3,"area":null},{"id":"2310.18868","title":"Correlation Aware Sparsified Mean Estimation Using Random Projection","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2401.05518","title":"Correlated Quantization for Faster Nonconvex Distributed Optimization","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2407.07421","title":"Federated PCA on Grassmann Manifold for IoT Anomaly Detection","created":"2024-07-10","cited_by_count":3,"area":null},{"id":"2412.01630","title":"Review of Mathematical Optimization in Federated Learning","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2510.22440","title":"Low-Precision Streaming PCA","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2107.14575","title":"DQ-SGD: Dynamic Quantization in SGD for Communication-Efficient Distributed Learning","created":"2021-07-30","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":"2302.11152","title":"Multi-Message Shuffled Privacy in Federated Learning","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2303.00035","title":"Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2305.07751","title":"Private and Communication-Efficient Algorithms for Entropy Estimation","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2310.11203","title":"Federated Learning with Nonvacuous Generalisation Bounds","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2310.16652","title":"How Robust is Federated Learning to Communication Error? A Comparison Study Between Uplink and Downlink Channels","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2312.08053","title":"Kimad: Adaptive Gradient Compression with Bandwidth Awareness","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2402.03158","title":"Optimal and Near-Optimal Adaptive Vector Quantization","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2403.08100","title":"Efficient Language Model Architectures for Differentially Private Federated Learning","created":"2024-03-12","cited_by_count":2,"area":null},{"id":"2406.03766","title":"Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networks","created":"2024-06-06","cited_by_count":2,"area":null}],"next_cursor":"100"}