{"total":26,"rows":[{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121,"area":null},{"id":"2311.18817","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","created":"2023-11-30","cited_by_count":80,"area":null},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2307.15196","title":"The Marginal Value of Momentum for Small Learning Rate SGD","created":"2023-07-27","cited_by_count":18,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2305.15659","title":"How to escape sharp minima with random perturbations","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2411.18607","title":"Task Arithmetic Through The Lens Of One-Shot Federated Learning","created":"2024-11-27","cited_by_count":12,"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":"2306.05862","title":"Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2310.20051","title":"The Expressibility of Polynomial based Attention Scheme","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2404.12293","title":"Singular-limit analysis of gradient descent with noise injection","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2603.05116","title":"FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning","created":"2026-03-05","cited_by_count":7,"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":"2311.10291","title":"Leveraging Function Space Aggregation for Federated Learning at Scale","created":"2023-11-17","cited_by_count":4,"area":null},{"id":"2404.11754","title":"Differentiated Aggregation to Improve Generalization in Federated Learning","created":"2024-04-17","cited_by_count":4,"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":"2409.07223","title":"Riemannian Federated Learning via Averaging Gradient Streams","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2501.04443","title":"Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis","created":"2025-01-08","cited_by_count":4,"area":null},{"id":"2401.13236","title":"How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learning","created":"2024-01-24","cited_by_count":2,"area":null},{"id":"2412.07971","title":"Effectiveness of Distributed Gradient Descent with Local Steps for Overparameterized Models","created":"2024-12-10","cited_by_count":1,"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":"2412.07210","title":"EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language Models","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2503.03139","title":"Convergence Analysis of Federated Learning Methods Using Backward Error Analysis","created":"2025-03-05","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":"2606.07495","title":"Second-Order Path Kernel Interpolation Formulas in Machine Learning","created":"2026-06-05","cited_by_count":0,"area":null}],"next_cursor":null}