% Key papers for SGD momentum and step-size schedules (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2018_don_28408,
  title = {{Don't Decay the Learning Rate, Increase the Batch Size}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/272},
}

@inproceedings{neurips2016_barzilai_55592,
  title = {{Barzilai-Borwein Step Size for Stochastic Gradient Descent}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7382},
}

@inproceedings{cvpr2018_a_12802,
  title = {{A PID Controller Approach for Stochastic Optimization of Deep Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/An_A_PID_Controller_CVPR_2018_paper.html},
}

@inproceedings{iclr2018_on_28672,
  title = {{On the insufficiency of existing momentum schemes for Stochastic Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/46},
}

@inproceedings{iclr2019_quasi_29009,
  title = {{Quasi-hyperbolic momentum and Adam for deep learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/716},
}

@inproceedings{aaai2016_learning_105015,
  title = {{Learning Step Size Controllers for Robust Neural Network Training}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10187},
}

@inproceedings{cvpr2018_geometry_13157,
  title = {{Geometry Aware Constrained Optimization Techniques for Deep Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Roy_Geometry_Aware_Constrained_CVPR_2018_paper.html},
}

@inproceedings{iclr2020_accelerating_29756,
  title = {{Accelerating SGD with momentum for over-parameterized learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=r1gixp4FPH},
}

@inproceedings{icml2019_sgd_37713,
  title = {{SGD: General Analysis and Improved Rates}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4155},
}

@inproceedings{icml2021_multiplicative_39639,
  title = {{Multiplicative Noise and Heavy Tails in Stochastic Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9187},
}

@inproceedings{neurips2020_an_59374,
  title = {{An Improved Analysis of Stochastic Gradient Descent with Momentum}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17487},
}

@inproceedings{icml2017_stochastic_36407,
  title = {{Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/856},
}

@inproceedings{icml2019_swalp_37715,
  title = {{SWALP : Stochastic Weight Averaging in Low Precision Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3602},
}

@inproceedings{icml2020_adascale_37903,
  title = {{AdaScale SGD: A User-Friendly Algorithm for Distributed Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6534},
}

@inproceedings{icml2019_optimal_37629,
  title = {{Optimal Mini-Batch and Step Sizes for SAGA}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4142},
}

@inproceedings{icml2016_starting_35987,
  title = {{Starting Small - Learning with Adaptive Sample Sizes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/daneshmand16.html},
}

@inproceedings{icml2021_a_38985,
  title = {{A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9527},
}

@inproceedings{neurips2019_beating_57944,
  title = {{Beating SGD Saturation with Tail-Averaging  and Minibatching}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14211},
}

@inproceedings{aaai2019_meta_101590,
  title = {{Meta-Descent for Online, Continual Prediction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4284},
}

@inproceedings{iclr2021_rmsprop_29983,
  title = {{RMSprop converges with proper hyper-parameter}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3374},
}

@inproceedings{neurips2024_on_71336,
  title = {{On the Convergence of Loss and Uncertainty-based Active Learning Algorithms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95912},
}

@inproceedings{iclr2024_the_33554,
  title = {{The Marginal Value of Momentum for Small Learning Rate SGD}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19521},
}

@inproceedings{neurips2024_derivatives_70680,
  title = {{Derivatives of Stochastic Gradient Descent in parametric optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96443},
}

@inproceedings{icml2024_stability_43844,
  title = {{Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to \$K\$-Level Stochastic Optimizations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34608},
}

@inproceedings{icml2024_momo_44610,
  title = {{MoMo: Momentum Models for Adaptive Learning Rates}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33842},
}

@inproceedings{icml2026_adaptive_51188,
  title = {{Adaptive Momentum and Nonlinear Damping for Neural Network Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=JWWpV4StVf},
}

@inproceedings{icml2026_the_51648,
  title = {{The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=OT9cxeWbEO},
}

@inproceedings{icml2026_adaptive_52585,
  title = {{Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=XMSaWRpEPS},
}

@inproceedings{icml2026_safeguarded_53904,
  title = {{Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=jqpLZEK3Zc},
}

@inproceedings{icml2026_on_55380,
  title = {{On the Role of Batch Size in Stochastic Conditional Gradient Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=yTFTLj7MoN},
}

@inproceedings{icml2026_step_55405,
  title = {{Step-Size Stability in Stochastic Optimization: A Theoretical Perspective}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=yhvzMLgpdV},
}

@inproceedings{neurips2025_enhancing_75595,
  title = {{Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=9t2OtyQ9mf},
}

@inproceedings{neurips2025_stab_76444,
  title = {{Stab-SGD: Noise-Adaptivity in Smooth Optimization with Stability Ratios}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=JRFMzQnYXl},
}

@inproceedings{iclr2025_sgd_82122,
  title = {{SGD with memory: fundamental properties and stochastic acceleration}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29667},
}

@inproceedings{iclr2025_gradient_82682,
  title = {{Gradient descent with generalized Newton’s method}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29116},
}

@inproceedings{iclr2025_the_83183,
  title = {{The AdEMAMix Optimizer: Better, Faster, Older}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28625},
}

@inproceedings{iclr2025_stochastic_83428,
  title = {{Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28388},
}

@inproceedings{iclr2025_on_83817,
  title = {{On the Performance Analysis of Momentum Method: A Frequency Domain Perspective}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28003},
}

@inproceedings{iclr2026_high_84679,
  title = {{High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=5OJLOwwXV4},
}

@inproceedings{neurips2026_perfect_90161,
  title = {{Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/155684},
}