% Key papers for Gradient flow and mean-field dynamics (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2019_wide_59205,
  title = {{Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13916},
}

@inproceedings{neurips2019_the_59059,
  title = {{The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13623},
}

@inproceedings{neurips2018_parameters_57500,
  title = {{Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11688},
}

@inproceedings{iclr2020_asymptotics_29590,
  title = {{Asymptotics of Wide Networks from Feynman Diagrams}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=S1gFvANKDS},
}

@inproceedings{neurips2019_maximum_58583,
  title = {{Maximum Mean Discrepancy Gradient Flow}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13759},
}

@inproceedings{neurips2020_dynamical_59752,
  title = {{Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17988},
}

@inproceedings{neurips2019_dynamics_58178,
  title = {{Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13224},
}

@inproceedings{neurips2020_complex_59557,
  title = {{Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18097},
}

@inproceedings{neurips2022_high_64868,
  title = {{High-dimensional limit theorems for SGD: Effective dynamics and critical scaling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54694},
}

@inproceedings{neurips2020_quantitative_60652,
  title = {{Quantitative Propagation of Chaos for SGD in Wide Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16803},
}

@inproceedings{neurips2018_mean_57363,
  title = {{Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/12011},
}

@inproceedings{neurips2020_generalization_59931,
  title = {{Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18471},
}

@inproceedings{neurips2022_phase_64444,
  title = {{Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54040},
}

@inproceedings{aaai2021_a_42,
  title = {{A Recipe for Global Convergence Guarantee in Deep Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08074-a-recipe-for-global-convergence-guarantee-in-deep-neural-networks/},
}

@inproceedings{icml2019_neuron_37574,
  title = {{Neuron birth-death dynamics accelerates gradient descent and converges asymptotically}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4286},
}

@inproceedings{neurips2021_last_63624,
  title = {{Last iterate convergence of SGD for Least-Squares in the Interpolation regime.}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28114},
}

@inproceedings{iclr2021_global_30200,
  title = {{Global Convergence of Three-layer Neural Networks in the Mean Field Regime}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2699},
}

@inproceedings{aaai2024_exact_5890,
  title = {{Exact, Fast and Expressive Poisson Point Processes via Squared Neural Families}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30041},
}

@inproceedings{neurips2022_whitening_65017,
  title = {{Whitening Convergence Rate of Coupling-based Normalizing Flows}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55358},
}

@inproceedings{neurips2022_convergence_66051,
  title = {{Convergence beyond the over-parameterized regime using Rayleigh quotients}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54755},
}

@inproceedings{neurips2024_learnability_70759,
  title = {{Learnability of high-dimensional targets by two-parameter models and gradient flow}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96367},
}

@inproceedings{neurips2024_4_72851,
  title = {{4+3 Phases of Compute-Optimal Neural Scaling Laws}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94549},
}

@inproceedings{neurips2024_large_73024,
  title = {{Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94399},
}

@inproceedings{neurips2025_asymptotics_76288,
  title = {{Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Hn8z3Ee4Xa},
}

@inproceedings{icml2024_stochastic_45021,
  title = {{Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33431},
}

@inproceedings{icml2024_keep_45051,
  title = {{Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33401},
}

@inproceedings{icml2025_deep_47358,
  title = {{Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45234},
}

@inproceedings{icml2026_balancing_49703,
  title = {{Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=4vztmTrGhd},
}

@inproceedings{icml2026_gradient_50352,
  title = {{Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=BXE3Z0EHCs},
}

@inproceedings{icml2026_taming_55400,
  title = {{Taming the Loss Landscape of PINNs with Noisy Feynman–Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=yd4tq9Rf3L},
}

@inproceedings{neurips2024_symmetries_71661,
  title = {{Symmetries in Overparametrized Neural Networks: A Mean Field View}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95619},
}

@inproceedings{neurips2025_from_77020,
  title = {{From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Pf3SVNhAQB},
}

@inproceedings{neurips2025_sad_77369,
  title = {{SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=T45dDL37V0},
}

@inproceedings{neurips2025_emergence_78956,
  title = {{Emergence and scaling laws in SGD learning of shallow neural networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=kA2H90nm26},
}

@inproceedings{neurips2025_learning_79132,
  title = {{Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=m3Sz3tFxIV},
}

@inproceedings{neurips2025_quantitative_79733,
  title = {{Quantitative convergence of trained neural networks to Gaussian processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=sTyrh0LjoH},
}

@inproceedings{neurips2025_dimension_79797,
  title = {{Dimension-adapted Momentum Outscales SGD}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=t4aN2G7Ucc},
}

@inproceedings{iclr2026_convergence_86896,
  title = {{Convergence Dynamics of Over-Parameterized Score Matching for a Single Gaussian}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=VDIH6L8ANo},
}

@inproceedings{neurips2026_convergence_89857,
  title = {{Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149087},
}