% Key papers for Neural tangent kernel analysis (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2016_exponential_55720,
  title = {{Exponential expressivity in deep neural networks through transient chaos}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7128},
}

@inproceedings{iclr2018_demystifying_28664,
  title = {{Demystifying MMD GANs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/54},
}

@inproceedings{iclr2019_adaptivity_28861,
  title = {{Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/895},
}

@inproceedings{icml2018_trainable_37058,
  title = {{Trainable Calibration Measures for Neural Networks from Kernel Mean Embeddings}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2326},
}

@inproceedings{icml2018_to_37051,
  title = {{To Understand Deep Learning We Need to Understand Kernel Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2026},
}

@inproceedings{neurips2019_what_59196,
  title = {{What Can ResNet Learn Efficiently, Going Beyond Kernels?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13949},
}

@inproceedings{cvpr2020_deep_15364,
  title = {{Deep Learning for Handling Kernel/model Uncertainty in Image Deconvolution}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{icml2019_a_37100,
  title = {{A Kernel Perspective for Regularizing Deep Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3832},
}

@inproceedings{neurips2020_on_60486,
  title = {{On the Similarity between the Laplace and Neural Tangent Kernels}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17244},
}

@inproceedings{neurips2020_why_61105,
  title = {{Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18036},
}

@inproceedings{icml2020_spectrum_38781,
  title = {{Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6524},
}

@inproceedings{neurips2020_spectra_60857,
  title = {{Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18253},
}

@inproceedings{iclr2017_deep_28250,
  title = {{Deep Information Propagation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=H1W1UN9gg},
}

@inproceedings{iclr2020_finite_29634,
  title = {{Finite Depth and Width Corrections to the Neural Tangent Kernel}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=SJgndT4KwB},
}

@inproceedings{iclr2021_a_30450,
  title = {{A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2543},
}

@inproceedings{iclr2018_initialization_28511,
  title = {{Initialization matters: Orthogonal Predictive State Recurrent Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/109},
}

@inproceedings{neurips2021_what_61923,
  title = {{What can linearized neural networks actually say about generalization?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27721},
}

@inproceedings{iclr2020_harnessing_29852,
  title = {{Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rkl8sJBYvH},
}

@inproceedings{neurips2021_locality_63296,
  title = {{Locality defeats the curse of dimensionality in convolutional teacher-student scenarios}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27703},
}

@inproceedings{aaai2022_rethinking_2644,
  title = {{Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/09082-rethinking-influence-functions-of-neural-networks-in-the-over-parameterized-regime/},
}

@inproceedings{iclr2024_pinnacle_34063,
  title = {{PINNACLE: PINN Adaptive ColLocation and Experimental points selection}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19012},
}

@inproceedings{neurips2024_the_71280,
  title = {{The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95966},
}

@inproceedings{iclr2025_how_82803,
  title = {{How Feature Learning Can Improve Neural Scaling Laws}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28996},
}

@inproceedings{aaai2025_when_11290,
  title = {{When Can We Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33690},
}

@inproceedings{icml2025_adaptive_47080,
  title = {{Adaptive kernel predictors from feature-learning infinite limits of neural networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45506},
}

@inproceedings{neurips2024_understanding_72082,
  title = {{Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95243},
}

@inproceedings{aaai2025_optimized_10218,
  title = {{Optimized Random Features for the Neural Tangent Kernel (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35244},
}

@inproceedings{iclr2024_faithful_35650,
  title = {{Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17423},
}

@inproceedings{icml2024_mean_43449,
  title = {{Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35003},
}

@inproceedings{icml2024_deep_44910,
  title = {{Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33542},
}

@inproceedings{icml2024_mean_45298,
  title = {{Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33154},
}

@inproceedings{icml2025_deep_46876,
  title = {{Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45702},
}

@inproceedings{icml2025_function_47023,
  title = {{Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45562},
}

@inproceedings{icml2025_from_48181,
  title = {{From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44430},
}

@inproceedings{icml2025_a_48438,
  title = {{A Bregman Proximal Viewpoint on Neural Operators}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44179},
}

@inproceedings{icml2026_pruning_52289,
  title = {{Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=UOpsG95XqH},
}

@inproceedings{neurips2024_relating_70498,
  title = {{Relating Hopfield Networks to Episodic Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96609},
}

@inproceedings{neurips2024_can_73056,
  title = {{Can neural operators always be continuously discretized?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94369},
}

@inproceedings{neurips2024_bounds_73735,
  title = {{Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93764},
}

@inproceedings{neurips2025_reproducing_74682,
  title = {{Reproducing Kernel Banach Space Models for Neural Networks with Application to Rademacher Complexity Analysis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=0398lUtZqs},
}