% Key papers for Normalization layer theory (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2017_self_56660,
  title = {{Self-Normalizing Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8891},
}

@inproceedings{neurips2019_understanding_59136,
  title = {{Understanding and Improving Layer Normalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13593},
}

@inproceedings{iclr2019_differentiable_29215,
  title = {{Differentiable Learning-to-Normalize via Switchable Normalization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1116},
}

@inproceedings{neurips2019_root_58926,
  title = {{Root Mean Square Layer Normalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14195},
}

@inproceedings{icml2020_on_38534,
  title = {{On Layer Normalization in the Transformer Architecture}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5811},
}

@inproceedings{iclr2019_fixup_28879,
  title = {{Fixup Initialization: Residual Learning Without Normalization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/643},
}

@inproceedings{icml2017_the_36428,
  title = {{The Shattered Gradients Problem: If resnets are the answer, then what is the question?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/601},
}

@inproceedings{iclr2017_identity_28393,
  title = {{Identity Matters in Deep Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=ryxB0Rtxx},
}

@inproceedings{aaai2016_shakeout_105030,
  title = {{Shakeout: A New Regularized Deep Neural Network Training Scheme}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10202},
}

@inproceedings{cvpr2019_ssn_14764,
  title = {{SSN: Learning Sparse Switchable Normalization via SparsestMax}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{neurips2021_why_62003,
  title = {{Why Spectral Normalization Stabilizes GANs: Analysis and Improvements}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28621},
}

@inproceedings{cvpr2019_instance_14323,
  title = {{Instance-Level Meta Normalization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{iclr2021_characterizing_30168,
  title = {{Characterizing signal propagation to close the performance gap in unnormalized ResNets}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3029},
}

@inproceedings{icml2019_differentiable_37284,
  title = {{Differentiable Dynamic Normalization for Learning Deep Representation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3623},
}

@inproceedings{neurips2020_batch_59431,
  title = {{Batch normalization provably avoids ranks collapse for randomly initialised deep networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18476},
}

@inproceedings{neurips2019_how_58376,
  title = {{How to Initialize your Network? Robust Initialization for WeightNorm \& ResNets}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14090},
}

@inproceedings{neurips2021_beyond_61677,
  title = {{Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27912},
}

@inproceedings{icml2019_jumpout_37459,
  title = {{Jumpout : Improved Dropout for Deep Neural Networks with ReLUs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3904},
}

@inproceedings{neurips2022_understanding_66427,
  title = {{Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53718},
}

@inproceedings{icml2019_characterizing_37216,
  title = {{Characterizing Well-Behaved vs. Pathological Deep Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4205},
}

@inproceedings{aaai2025_till_10998,
  title = {{Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers.}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34058},
}

@inproceedings{neurips2024_normalization_72769,
  title = {{Normalization and effective learning rates in reinforcement learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94626},
}

@inproceedings{iclr2024_towards_35625,
  title = {{Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17448},
}

@inproceedings{icml2024_on_43289,
  title = {{On the Nonlinearity of Layer Normalization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35163},
}

@inproceedings{icml2025_peri_47929,
  title = {{Peri-LN: Revisiting Normalization Layer in the Transformer Architecture}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44675},
}

@inproceedings{icml2026_bounded_50141,
  title = {{Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=9M6kY6yuAy},
}

@inproceedings{neurips2025_learning_78315,
  title = {{Learning in Compact Spaces with Approximately Normalized Transformer}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=dH8mKmvADv},
}

@inproceedings{icml2025_on_49124,
  title = {{On the Importance of Gaussianizing Representations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43501},
}