{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1911.00222","title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","created":"2019-11-01","cited_by_count":536},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"2405.15682","title":"The Road Less Scheduled","created":"2024-05-24","cited_by_count":163},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"2010.02372","title":"Lower Bounds and Optimal Algorithms for Personalized Federated Learning","created":"2020-10-05","cited_by_count":123},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"2402.15627","title":"MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs","created":"2024-02-23","cited_by_count":112},{"id":"2209.01188","title":"Petals: Collaborative Inference and Fine-tuning of Large Models","created":"2022-09-02","cited_by_count":87},{"id":"2006.08950","title":"Federated Accelerated Stochastic Gradient Descent","created":"2020-06-16","cited_by_count":85},{"id":"2302.12022","title":"DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule","created":"2023-02-08","cited_by_count":85},{"id":"2301.09604","title":"FedExP: Speeding Up Federated Averaging via Extrapolation","created":"2023-01-23","cited_by_count":69},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55},{"id":"2103.05032","title":"Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning","created":"2021-03-08","cited_by_count":52},{"id":"1904.10120","title":"Semi-Cyclic Stochastic Gradient Descent","created":"2019-04-23","cited_by_count":40},{"id":"2111.03741","title":"Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective","created":"2021-11-05","cited_by_count":38},{"id":"2206.12949","title":"Cross-Silo Federated Learning: Challenges and Opportunities","created":"2022-06-26","cited_by_count":38},{"id":"2007.00878","title":"On the Outsized Importance of Learning Rates in Local Update Methods","created":"2020-07-02","cited_by_count":36},{"id":"2110.10342","title":"Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond","created":"2021-10-20","cited_by_count":36},{"id":"2102.06704","title":"Proximal and Federated Random Reshuffling","created":"2021-02-12","cited_by_count":33},{"id":"2102.03198","title":"Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning","created":"2021-02-05","cited_by_count":31},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30},{"id":"2303.01215","title":"Why (and When) does Local SGD Generalize Better than SGD?","created":"2023-03-02","cited_by_count":26},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26},{"id":"2407.07852","title":"OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training","created":"2024-07-10","cited_by_count":24},{"id":"2201.11066","title":"Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization","created":"2022-01-26","cited_by_count":23},{"id":"2102.07245","title":"Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization","created":"2021-02-14","cited_by_count":21},{"id":"2412.01152","title":"INTELLECT-1 Technical Report","created":"2024-12-02","cited_by_count":21},{"id":"2110.08133","title":"Trade-offs of Local SGD at Scale: An Empirical Study","created":"2021-10-15","cited_by_count":20},{"id":"2312.12670","title":"On the Role of Server Momentum in Federated Learning","created":"2023-12-19","cited_by_count":16},{"id":"2205.03914","title":"Federated Random Reshuffling with Compression and Variance Reduction","created":"2022-05-08","cited_by_count":12},{"id":"2405.11667","title":"The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication","created":"2024-05-19","cited_by_count":12},{"id":"2403.10616","title":"DiPaCo: Distributed Path Composition","created":"2024-03-15","cited_by_count":10},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10},{"id":"2405.13766","title":"The Power of Extrapolation in Federated Learning","created":"2024-05-22","cited_by_count":10},{"id":"2403.07128","title":"DrJAX: Scalable and Differentiable MapReduce Primitives in JAX","created":"2024-03-11","cited_by_count":9},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5},{"id":"2405.09394","title":"SPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning","created":"2024-05-15","cited_by_count":5},{"id":"2405.14446","title":"Worldwide Federated Training of Language Models","created":"2024-05-23","cited_by_count":5},{"id":"2410.01410","title":"On the Convergence of FedProx with Extrapolation and Inexact Prox","created":"2024-10-02","cited_by_count":3}],"next_cursor":null}