% Key papers for Shallow ReLU network convergence (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2019_a_37095,
  title = {{A Convergence Theory for Deep Learning via Over-Parameterization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4040},
}

@inproceedings{cvpr2020_eternal_15491,
  title = {{Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{iclr2019_gradient_29003,
  title = {{Gradient Descent Provably Optimizes Over-parameterized Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/956},
}

@inproceedings{neurips2018_learning_57291,
  title = {{Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11781},
}

@inproceedings{neurips2017_convergence_56216,
  title = {{Convergence Analysis of Two-layer Neural Networks with ReLU Activation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8855},
}

@inproceedings{neurips2019_on_58710,
  title = {{On Lazy Training in Differentiable Programming}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13477},
}

@inproceedings{icml2019_fine_37372,
  title = {{Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3996},
}

@inproceedings{icml2019_gradient_37403,
  title = {{Gradient Descent Finds Global Minima of Deep Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3786},
}

@inproceedings{cvpr2016_learning_11662,
  title = {{Learning Local Image Descriptors With Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{icml2017_the_36424,
  title = {{The Loss Surface of Deep and Wide Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/724},
}

@inproceedings{neurips2019_generalization_58320,
  title = {{Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14592},
}

@inproceedings{aaai2018_building_102458,
  title = {{Building Deep Networks on Grassmann Manifolds}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11725},
}

@inproceedings{cvpr2017_global_12316,
  title = {{Global Optimality in Neural Network Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{neurips2019_on_58725,
  title = {{On the Convergence Rate of Training Recurrent Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13775},
}

@inproceedings{iclr2019_a_29059,
  title = {{A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/789},
}

@inproceedings{iclr2018_learning_28457,
  title = {{Learning One-hidden-layer Neural Networks with Landscape Design}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/119},
}

@inproceedings{neurips2019_an_57897,
  title = {{An Improved Analysis of Training Over-parameterized Deep Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13408},
}

@inproceedings{iclr2019_a_29082,
  title = {{A Mean Field Theory of Batch Normalization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/802},
}

@inproceedings{icml2017_globally_36207,
  title = {{Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/571},
}

@inproceedings{icml2017_an_36062,
  title = {{An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/550},
}

@inproceedings{icml2024_the_45091,
  title = {{The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33361},
}

@inproceedings{icml2024_activation_44018,
  title = {{Activation-Descent Regularization for Input Optimization of ReLU Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34434},
}

@inproceedings{iclr2025_loss_83477,
  title = {{Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28339},
}

@inproceedings{iclr2024_benign_33883,
  title = {{Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19192},
}

@inproceedings{iclr2024_on_34918,
  title = {{On the Parameterization of Second-Order Optimization Effective towards the Infinite Width}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18156},
}

@inproceedings{iclr2024_random_35372,
  title = {{Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17701},
}

@inproceedings{icml2024_convex_44726,
  title = {{Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33726},
}

@inproceedings{icml2025_transformative_47804,
  title = {{Transformative or Conservative? Conservation laws for ResNets and Transformers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44796},
}

@inproceedings{icml2025_feature_48382,
  title = {{Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44234},
}

@inproceedings{icml2025_simplicity_48665,
  title = {{Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43957},
}

@inproceedings{icml2026_sharp_54088,
  title = {{Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=lk5T4FMxlm},
}

@inproceedings{neurips2024_topological_70374,
  title = {{Topological obstruction to the training of shallow ReLU neural networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96726},
}

@inproceedings{neurips2024_neural_70656,
  title = {{Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96466},
}

@inproceedings{neurips2024_stable_70672,
  title = {{Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96450},
}

@inproceedings{neurips2024_benign_70732,
  title = {{Benign overfitting in leaky ReLU networks with moderate input dimension}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96392},
}

@inproceedings{neurips2025_optimal_75387,
  title = {{Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=7VN0iICXZj},
}

@inproceedings{neurips2025_convex_77379,
  title = {{Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=T9OQ094qR8},
}

@inproceedings{neurips2025_convergence_78351,
  title = {{Convergence of the Gradient Flow for Shallow ReLU Networks on Weakly Interacting Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=dkXDyM66ce},
}

@inproceedings{neurips2025_improved_78919,
  title = {{Improved Scaling Laws in Linear Regression via Data Reuse}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=jeen4x145W},
}

@inproceedings{neurips2025_block_79778,
  title = {{Block Coordinate Descent for Neural Networks Provably Finds Global Minima}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=stUD2uNafM},
}