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

@inproceedings{neurips2017_qsgd_56602,
  title = {{QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8961},
}

@inproceedings{neurips2017_terngrad_56712,
  title = {{TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8942},
}

@inproceedings{neurips2019_qsparse_58860,
  title = {{Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14381},
}

@inproceedings{neurips2018_sparsified_57639,
  title = {{Sparsified SGD with Memory}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11439},
}

@inproceedings{neurips2018_atomo_56827,
  title = {{ATOMO: Communication-efficient Learning via Atomic Sparsification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11935},
}

@inproceedings{icml2019_error_37339,
  title = {{Error Feedback Fixes SignSGD and other Gradient Compression Schemes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4158},
}

@inproceedings{aaai2018_adacomp_102461,
  title = {{AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11728},
}

@inproceedings{icml2019_on_37609,
  title = {{On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3779},
}

@inproceedings{icml2018_communication_36577,
  title = {{Communication-Computation Efficient Gradient Coding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1994},
}

@inproceedings{neurips2018_a_56799,
  title = {{A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11261},
}

@inproceedings{icml2019_doublesqueeze_37312,
  title = {{DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4191},
}

@inproceedings{icml2018_signsgd_37088,
  title = {{signSGD: Compressed Optimisation for Non-Convex Problems}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2356},
}

@inproceedings{neurips2019_communication_58006,
  title = {{Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14131},
}

@inproceedings{iclr2020_slowmo_29698,
  title = {{SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=SkxJ8REYPH},
}

@inproceedings{aaai2020_on_101933,
  title = {{On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5793},
}

@inproceedings{neurips2019_communication_58007,
  title = {{Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13513},
}

@inproceedings{icml2019_trading_37813,
  title = {{Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4289},
}

@inproceedings{aaai2019_scalable_101750,
  title = {{Scalable Distributed DL Training: Batching Communication and Computation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4465},
}

@inproceedings{neurips2020_adaptive_59322,
  title = {{Adaptive Gradient Quantization for Data-Parallel SGD}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16956},
}

@inproceedings{icml2018_error_36672,
  title = {{Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2148},
}

@inproceedings{neurips2024_exponential_73284,
  title = {{Exponential Quantum Communication Advantage in Distributed Inference and Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94157},
}

@inproceedings{neurips2025_sketched_77756,
  title = {{Sketched Adaptive Distributed Deep Learning: A Sharp Convergence Analysis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=XIeE8jbM4K},
}

@inproceedings{iclr2024_a_35674,
  title = {{A Quadratic Synchronization Rule for Distributed Deep Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17399},
}

@inproceedings{neurips2025_acco_74853,
  title = {{ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=1qKUVyymXs},
}

@inproceedings{iclr2026_demo_86806,
  title = {{DeMo: Decoupled Momentum Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=U9oewpa7cn},
}

@inproceedings{iclr2026_error_88846,
  title = {{Error Feedback for Muon and Friends}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=rex7s82Iav},
}

@inproceedings{aaai2026_detonation_106904,
  title = {{DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39256},
}

@inproceedings{icml2025_distributed_48811,
  title = {{Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43811},
}

@inproceedings{iclr2026_des_84767,
  title = {{DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=6N2qFixxYZ},
}

@inproceedings{iclr2026_legacy_85381,
  title = {{LEGACY: A Lightweight Dynamic Gradient Compression Strategy for Distributed Deep Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=DsBYEO3B8O},
}

@inproceedings{neurips2026_clapping_95323,
  title = {{Clapping: Removing Per-sample Storage for Pipeline Parallel Learning with Communication Compression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/148239},
}