% Key papers for Local and asynchronous SGD (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2020_on_29482,
  title = {{On the Convergence of FedAvg on Non-IID Data}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=HJxNAnVtDS},
}

@inproceedings{aaai2019_parallel_101799,
  title = {{Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4514},
}

@inproceedings{neurips2017_can_56188,
  title = {{Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9308},
}

@inproceedings{icml2017_gradient_36209,
  title = {{Gradient Coding: Avoiding Stragglers in Distributed Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/851},
}

@inproceedings{iclr2020_don_29243,
  title = {{Don't Use Large Mini-batches, Use Local SGD}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=B1eyO1BFPr},
}

@inproceedings{iclr2019_local_29010,
  title = {{Local SGD Converges Fast and Communicates Little}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/979},
}

@inproceedings{icml2017_asynchronous_36072,
  title = {{Asynchronous Stochastic Gradient Descent with Delay Compensation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/564},
}

@inproceedings{iclr2018_large_28706,
  title = {{Large scale distributed neural network training through online distillation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/255},
}

@inproceedings{icml2019_stochastic_37764,
  title = {{Stochastic Gradient Push for Distributed Deep Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3899},
}

@inproceedings{iclr2019_signsgd_28784,
  title = {{signSGD with Majority Vote is Communication Efficient and Fault Tolerant}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/876},
}

@inproceedings{neurips2019_local_58554,
  title = {{Local SGD with  Periodic Averaging: Tighter Analysis  and Adaptive Synchronization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14104},
}

@inproceedings{icml2020_is_38347,
  title = {{Is Local SGD Better than Minibatch SGD?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6812},
}

@inproceedings{aaai2016_fast_105133,
  title = {{Fast Asynchronous Parallel Stochastic Gradient Descent: A Lock-Free Approach with Convergence Guarantee}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10305},
}

@inproceedings{aaai2022_demystifying_1965,
  title = {{Demystifying Why Local Aggregation Helps: Convergence Analysis of Hierarchical SGD}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/08548-demystifying-why-local-aggregation-helps-convergence-analysis-of-hierarchical-sgd/},
}

@inproceedings{icml2018_asynchronous_36525,
  title = {{Asynchronous Decentralized Parallel Stochastic Gradient Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2423},
}

@inproceedings{neurips2020_minibatch_60317,
  title = {{Minibatch vs Local SGD for Heterogeneous Distributed Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18957},
}

@inproceedings{neurips2020_a_59240,
  title = {{A Decentralized Parallel Algorithm for Training Generative Adversarial Nets}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17279},
}

@inproceedings{icml2018_distributed_36650,
  title = {{Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2293},
}

@inproceedings{neurips2020_distributed_59722,
  title = {{Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18179},
}

@inproceedings{icml2020_moniqua_38467,
  title = {{Moniqua: Modulo Quantized Communication in Decentralized SGD}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5885},
}

@inproceedings{aaai2024_towards_7622,
  title = {{Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29477},
}

@inproceedings{aaai2025_adagk_8018,
  title = {{AdaGK-SGD: Adaptive Global Knowledge Guided Distributed Stochastic Gradient Descent}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34365},
}

@inproceedings{neurips2024_leveraging_72068,
  title = {{Leveraging partial stragglers within gradient coding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95255},
}

@inproceedings{neurips2024_efficient_74292,
  title = {{Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93266},
}

@inproceedings{neurips2025_unveiling_77553,
  title = {{Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=V8dGVO5Xpg},
}

@inproceedings{iclr2025_scalable_81166,
  title = {{Scalable Decentralized Learning with Teleportation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30604},
}

@inproceedings{iclr2024_flag_33721,
  title = {{Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19354},
}

@inproceedings{icml2025_efficient_46179,
  title = {{Efficient Distributed Optimization under Heavy-Tailed Noise}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46381},
}

@inproceedings{icml2025_halos_46989,
  title = {{HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45594},
}

@inproceedings{icml2025_ringmaster_47325,
  title = {{Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45264},
}

@inproceedings{icml2025_constant_48758,
  title = {{Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43864},
}

@inproceedings{icml2026_clipping_50278,
  title = {{Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=AmgjQp4vrr},
}

@inproceedings{icml2026_improved_54497,
  title = {{Improved Convergence Analysis of Topology Dependence in Decentralized SGD}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=pYI0WjV5iM},
}

@inproceedings{neurips2024_shadowheart_71914,
  title = {{Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95390},
}

@inproceedings{neurips2024_ordered_72354,
  title = {{Ordered Momentum for Asynchronous SGD}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94995},
}

@inproceedings{neurips2025_approximate_77121,
  title = {{Approximate Gradient Coding for Distributed Learning with Heterogeneous Stragglers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=QlDyoo8qLY},
}

@inproceedings{neurips2025_revisiting_79896,
  title = {{Revisiting Consensus Error: A Fine-grained Analysis of Local SGD under Second-order Data Heterogeneity}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=u1QFeoxnhW},
}

@inproceedings{iclr2025_from_83314,
  title = {{From Promise to Practice: Realizing High-performance Decentralized Training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28499},
}

@inproceedings{iclr2025_local_83322,
  title = {{Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28491},
}

@inproceedings{neurips2026_do_93148,
  title = {{Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/155336},
}