{"total":20,"rows":[{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2303.01215","title":"Why (and When) does Local SGD Generalize Better than SGD?","created":"2023-03-02","cited_by_count":26,"area":null},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2210.11948","title":"lo-fi: distributed fine-tuning without communication","created":"2022-10-19","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":"2508.15706","title":"Overcoming the Communication-Performance Tradeoff in LLM Pretraining","created":"2025-08-21","cited_by_count":12,"area":null},{"id":"2405.17517","title":"WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2509.10439","title":"Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration","created":"2025-09-12","cited_by_count":9,"area":null},{"id":"2406.02613","title":"ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2406.13936","title":"Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2312.02204","title":"Meta-learning Optimizers for Communication-Efficient Learning","created":"2023-12-02","cited_by_count":2,"area":null},{"id":"2409.03863","title":"Can We Theoretically Quantify the Impacts of Local Updates on the Generalization Performance of Federated Learning?","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2411.02908","title":"Photon: Federated LLM Pre-Training","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2504.18454","title":"Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2507.20424","title":"Communication-Efficient Distributed Training for Collaborative Flat Optima Recovery in Deep Learning","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2608.06563","title":"Theoretical Foundations of Communication-Efficient, Robust, and Practical Distributed and Federated Optimization","created":"2026-08-06","cited_by_count":0,"area":null}],"next_cursor":null}