{"total":21,"rows":[{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2503.09799","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","created":"2025-03-12","cited_by_count":27,"area":null},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2502.12996","title":"Eager Updates For Overlapped Communication and Computation in DiLoCo","created":"2025-02-18","cited_by_count":11,"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":"2502.04164","title":"Efficient Distributed Optimization under Heavy-Tailed Noise","created":"2025-02-06","cited_by_count":7,"area":null},{"id":"2502.19385","title":"HDEE: Heterogeneous Domain Expert Ensemble","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2502.19913","title":"SkipPipe: Partial and Reordered Pipelining Framework for Training LLMs in Heterogeneous Networks","created":"2025-02-27","cited_by_count":4,"area":null},{"id":"2506.21263","title":"DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster","created":"2025-06-26","cited_by_count":4,"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":"2502.13811","title":"On the Duality between Gradient Transformations and Adapters","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2507.17346","title":"Taming Latency and Bandwidth: A Theoretical Framework and Adaptive Algorithm for Communication-Constrained Training","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2603.26954","title":"High dimensional theory of two-phase optimizers","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2606.05484","title":"Learned Subspace Compression for Communication-Efficient Pipeline Parallelism","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2605.24538","title":"Is Decentralized AI Governable? From Regulative Policy to Constitutive Protocol","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.02958","title":"Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.24722","title":"Decentralised AI Training and Inference with BlockTrain","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.02544","title":"Not Every Sync Is Safe: Calibrated DiLoCo Scheduling for Shared AI Infrastructure","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.14339","title":"Communication-Efficient LLM Adaptation over Decentralized GPU Meshes","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.36662","title":"AutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04867","title":"Greedy Local Learning for Language Model Pretraining: Gaps and Objective Design","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}