% Key papers for Stability-based generalization analysis (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2017_understanding_28334,
  title = {{Understanding deep learning requires rethinking generalization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=Sy8gdB9xx},
}

@inproceedings{iclr2020_deep_29244,
  title = {{Deep Double Descent: Where Bigger Models and More Data Hurt}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=B1g5sA4twr},
}

@inproceedings{neurips2017_train_56735,
  title = {{Train longer, generalize better: closing the generalization gap in large batch training of neural networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8963},
}

@inproceedings{neurips2018_understanding_57737,
  title = {{Understanding Batch Normalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11739},
}

@inproceedings{neurips2016_matrix_55863,
  title = {{Matrix Completion has No Spurious Local Minimum}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7218},
}

@inproceedings{icml2018_curriculum_36605,
  title = {{Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2021},
}

@inproceedings{cvpr2017_noisy_12491,
  title = {{Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{icml2017_sharp_36393,
  title = {{Sharp Minima Can Generalize For Deep Nets}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/607},
}

@inproceedings{neurips2017_regularizing_56621,
  title = {{Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9287},
}

@inproceedings{neurips2019_towards_59102,
  title = {{Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14601},
}

@inproceedings{neurips2019_control_58040,
  title = {{Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13337},
}

@inproceedings{neurips2020_the_60954,
  title = {{The Pitfalls of Simplicity Bias in Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16934},
}

@inproceedings{iclr2020_can_29853,
  title = {{Can gradient clipping mitigate label noise?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rklB76EKPr},
}

@inproceedings{iclr2019_theoretical_29190,
  title = {{Theoretical Analysis of Auto Rate-Tuning by Batch Normalization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/960},
}

@inproceedings{icml2019_on_37596,
  title = {{On Symmetric Losses for Learning from Corrupted Labels}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3697},
}

@inproceedings{icml2020_do_38122,
  title = {{Do We Need Zero Training Loss After Achieving Zero Training Error?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6799},
}

@inproceedings{neurips2019_asymmetric_57917,
  title = {{Asymmetric Valleys: Beyond Sharp and Flat Local Minima}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14506},
}

@inproceedings{aaai2020_generalization_101876,
  title = {{Generalization Error Bounds of Gradient Descent for Learning Over-Parameterized Deep ReLU Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5736},
}

@inproceedings{iclr2019_deterministic_28977,
  title = {{Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/954},
}

@inproceedings{neurips2019_data_58085,
  title = {{Data Cleansing for Models Trained with SGD}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13578},
}

@inproceedings{neurips2024_neglected_73725,
  title = {{Neglected Hessian component explains mysteries in sharpness regularization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93774},
}

@inproceedings{aaai2025_a_7905,
  title = {{A Method for Enhancing Generalization of Adam by Multiple Integrations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32435},
}

@inproceedings{aaai2025_from_9246,
  title = {{From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35389},
}

@inproceedings{neurips2024_changing_74607,
  title = {{Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92982},
}

@inproceedings{neurips2025_differentiable_75466,
  title = {{Differentiable Sparsity via \$D\$-Gating: Simple and Versatile Structured Penalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=8OGTkEJrmb},
}

@inproceedings{iclr2025_grokking_82290,
  title = {{Grokking at the Edge of Numerical Stability}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29501},
}

@inproceedings{icml2024_simplicity_44539,
  title = {{Simplicity Bias via Global Convergence of Sharpness Minimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33913},
}

@inproceedings{icml2026_revisiting_52996,
  title = {{Revisiting the Volume Hypothesis}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=b0agSl1SMw},
}

@inproceedings{icml2026_flat_54940,
  title = {{Flat Minima and Generalization: Insights from Stochastic Convex Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=u6zp8zZ8Ou},
}

@inproceedings{icml2026_optimization_55397,
  title = {{Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ya4nicrVDf},
}

@inproceedings{neurips2024_deep_71883,
  title = {{Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting \& Beyond}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95420},
}

@inproceedings{neurips2024_exact_73926,
  title = {{Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93585},
}

@inproceedings{neurips2025_multiclass_76075,
  title = {{Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=FBjTMq2Rby},
}

@inproceedings{neurips2025_how_76416,
  title = {{How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Izewdgcl8U},
}

@inproceedings{neurips2025_when_77567,
  title = {{When Does Curriculum Learning Help? A Theoretical Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=VIP5mV8x0b},
}

@inproceedings{neurips2025_exploring_77826,
  title = {{Exploring Landscapes for Better Minima along Valleys}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=XxRKqFsvoK},
}

@inproceedings{iclr2026_generalization_89491,
  title = {{Generalization Below the Edge of Stability: The Role of Data Geometry}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=zVmS7G6Dyi},
}

@inproceedings{aaai2026_tractable_107419,
  title = {{Tractable Sharpness-Aware Learning of Probabilistic Circuits}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39771},
}

@inproceedings{neurips2026_on_90436,
  title = {{On Generalization in Bilevel Optimization with Overparameterized Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149738},
}

@inproceedings{neurips2026_position_91586,
  title = {{Position: Lottery Tickets Do Not Explain Overparameterization. How About Escape Dimensions?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/140102},
}