% Key papers for Adam convergence and adaptive learning rates (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2019_decoupled_28799,
  title = {{Decoupled Weight Decay Regularization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/935},
}

@inproceedings{iclr2018_on_28716,
  title = {{On the Convergence of Adam and Beyond}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/78},
}

@inproceedings{iclr2020_on_29848,
  title = {{On the Variance of the Adaptive Learning Rate and Beyond}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rkgz2aEKDr},
}

@inproceedings{neurips2017_the_56718,
  title = {{The Marginal Value of Adaptive Gradient Methods in Machine Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9195},
}

@inproceedings{cvpr2019_a_13794,
  title = {{A Sufficient Condition for Convergences of Adam and RMSProp}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{neurips2019_lookahead_58560,
  title = {{Lookahead Optimizer: k steps forward, 1 step back}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13994},
}

@inproceedings{iclr2019_adaptive_28798,
  title = {{Adaptive Gradient Methods with Dynamic Bound of Learning Rate}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/974},
}

@inproceedings{neurips2020_adabelief_59313,
  title = {{AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16809},
}

@inproceedings{iclr2021_adamp_30175,
  title = {{AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2880},
}

@inproceedings{icml2018_dissecting_36647,
  title = {{Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2002},
}

@inproceedings{iclr2018_online_28456,
  title = {{Online Learning Rate Adaptation with Hypergradient Descent}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/14},
}

@inproceedings{neurips2020_why_61107,
  title = {{Why are Adaptive Methods Good for Attention Models?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18194},
}

@inproceedings{aaai2021_on_1091,
  title = {{On the Adequacy of Untuned Warmup for Adaptive Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08828-on-the-adequacy-of-untuned-warmup-for-adaptive-optimization/},
}

@inproceedings{neurips2018_l4_57262,
  title = {{L4: Practical loss-based stepsize adaptation for deep learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11622},
}

@inproceedings{iclr2019_adashift_28941,
  title = {{AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/718},
}

@inproceedings{icml2021_how_39428,
  title = {{How Do Adam and Training Strategies Help BNNs Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8613},
}

@inproceedings{iclr2019_deep_29087,
  title = {{Deep Frank-Wolfe For Neural Network Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/975},
}

@inproceedings{neurips2019_metainit_58597,
  title = {{MetaInit: Initializing learning by learning to initialize}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14216},
}

@inproceedings{aaai2019_hyperadam_101751,
  title = {{HyperAdam: A Learnable Task-Adaptive Adam for Network Training}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4466},
}

@inproceedings{icml2022_adaptive_40223,
  title = {{Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17065},
}

@inproceedings{neurips2024_why_72584,
  title = {{Why Transformers Need Adam: A Hessian Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94790},
}

@inproceedings{aaai2024_zo_7840,
  title = {{ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-Order Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29796},
}

@inproceedings{neurips2024_surge_73362,
  title = {{Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94086},
}

@inproceedings{icml2024_prodigy_44067,
  title = {{Prodigy: An Expeditiously Adaptive Parameter-Free Learner}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34385},
}

@inproceedings{iclr2026_cautious_89462,
  title = {{Cautious Optimizers: Improving Training with One Line of Code}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=zBPZeRjfgu},
}

@inproceedings{icml2024_understanding_45086,
  title = {{Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33366},
}

@inproceedings{neurips2024_adopt_74129,
  title = {{ADOPT: Modified Adam Can Converge with Any \$beta\_2\$ with the Optimal Rate}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93408},
}

@inproceedings{neurips2024_microadam_72324,
  title = {{MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95023},
}

@inproceedings{aaai2025_hvadam_9397,
  title = {{HVAdam: A Full-Dimension Adaptive Optimizer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34421},
}

@inproceedings{iclr2024_lion_34842,
  title = {{Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18232},
}

@inproceedings{icml2024_studying_45274,
  title = {{Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33178},
}

@inproceedings{icml2024_mada_45576,
  title = {{MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32876},
}

@inproceedings{icml2024_can_45684,
  title = {{Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32768},
}

@inproceedings{icml2025_a_46525,
  title = {{A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46043},
}

@inproceedings{icml2025_bso_47509,
  title = {{BSO: Binary Spiking Online Optimization Algorithm}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45087},
}

@inproceedings{icml2026_understanding_49645,
  title = {{Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=4MVVscCjYu},
}

@inproceedings{icml2026_adaptive_52070,
  title = {{Adaptive Preconditioners Trigger Loss Spikes in Adam}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=STWQoscanw},
}

@inproceedings{icml2026_decoupling_53014,
  title = {{Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=bCxkeiNGxZ},
}

@inproceedings{icml2026_towards_54983,
  title = {{Towards Understanding Adam Convergence on Highly Degenerate Polynomials}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=uYWVGk1Qt0},
}

@inproceedings{icml2026_delving_55302,
  title = {{Delving into Muon and Beyond: Deep Analysis and Extensions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=xUQ0Gw11NL},
}