% Key papers for Weight normalization and decay interplay (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2017_on_36314,
  title = {{On Calibration of Modern Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/808},
}

@inproceedings{icml2018_gradnorm_36719,
  title = {{GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2419},
}

@inproceedings{cvpr2017_linking_12434,
  title = {{Linking Image and Text With 2-Way Nets}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{iclr2018_flipout_28670,
  title = {{Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/35},
}

@inproceedings{iclr2018_deep_28485,
  title = {{Deep Complex Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/2},
}

@inproceedings{cvpr2017_improving_12352,
  title = {{Improving Training of Deep Neural Networks via Singular Value Bounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{icml2017_on_36321,
  title = {{On the Expressive Power of Deep Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/841},
}

@inproceedings{cvpr2020_continual_15281,
  title = {{Continual Learning With Extended Kronecker-Factored Approximate Curvature}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2019_riemannian_58917,
  title = {{Riemannian batch normalization for SPD neural networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14444},
}

@inproceedings{cvpr2019_dynamic_14120,
  title = {{Dynamic Recursive Neural Network}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{neurips2019_she_58929,
  title = {{SHE: A Fast and Accurate Deep Neural Network for Encrypted Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14025},
}

@inproceedings{neurips2019_backpropagation_57931,
  title = {{Backpropagation-Friendly Eigendecomposition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13496},
}

@inproceedings{iclr2019_on_28916,
  title = {{On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/949},
}

@inproceedings{cvpr2024_batch_22820,
  title = {{Batch Normalization Alleviates the Spectral Bias in Coordinate Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30964},
}

@inproceedings{iclr2020_stochastic_29879,
  title = {{Stochastic Weight Averaging in Parallel: Large-Batch Training That Generalizes Well}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rygFWAEFwS},
}

@inproceedings{icml2022_set_41169,
  title = {{Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16893},
}

@inproceedings{neurips2021_fast_62188,
  title = {{Fast Certified Robust Training with Short Warmup}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26903},
}

@inproceedings{iclr2019_dynamic_28878,
  title = {{Dynamic Sparse Graph for Efficient Deep Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/650},
}

@inproceedings{iclr2022_fast_30782,
  title = {{Fast Differentiable Matrix Square Root}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6545},
}

@inproceedings{iclr2019_equi_29123,
  title = {{Equi-normalization of Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/941},
}

@inproceedings{neurips2024_analyzing_72777,
  title = {{Analyzing \& Reducing the Need for Learning Rate Warmup in GPT Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94618},
}

@inproceedings{cvpr2025_dynamic_26041,
  title = {{Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34948},
}

@inproceedings{iclr2024_a_35267,
  title = {{A Lie Group Approach to Riemannian Batch Normalization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17806},
}

@inproceedings{icml2026_batch_50719,
  title = {{Batch Normalization for Neural Networks on Complex Domains}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=F7aqfPhbYI},
}

@inproceedings{icml2026_simplegpt_53044,
  title = {{SimpleGPT: Improving GPT via A Simple Normalization Strategy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=bT6JcLswlW},
}

@inproceedings{icml2026_sparseopt_54350,
  title = {{SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=o9JP7N8YO9},
}

@inproceedings{neurips2024_normalization_72213,
  title = {{Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95128},
}

@inproceedings{neurips2024_improving_70944,
  title = {{Improving Neural ODE Training with Temporal Adaptive Batch Normalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96259},
}