% Key papers for Low-rank and single-index recovery (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2017_a_104489,
  title = {{A Riemannian Network for SPD Matrix Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10866},
}

@inproceedings{neurips2016_global_55757,
  title = {{Global Optimality of Local Search for Low Rank Matrix Recovery}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7053},
}

@inproceedings{neurips2018_on_57468,
  title = {{On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11309},
}

@inproceedings{icml2016_low_35896,
  title = {{Low-rank Solutions of Linear Matrix Equations via Procrustes Flow}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/tu16.html},
}

@inproceedings{neurips2017_learning_56431,
  title = {{Learning ReLUs via Gradient Descent}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8989},
}

@inproceedings{neurips2017_sgd_56640,
  title = {{SGD Learns the Conjugate Kernel Class of the Network}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9029},
}

@inproceedings{icml2018_gradient_36724,
  title = {{Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1980},
}

@inproceedings{iclr2019_subgradient_28946,
  title = {{Subgradient Descent Learns Orthogonal Dictionaries}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/904},
}

@inproceedings{neurips2018_statistical_57645,
  title = {{Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11777},
}

@inproceedings{neurips2018_learning_57331,
  title = {{Learning with SGD and Random Features}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11966},
}

@inproceedings{aaai2019_lifted_101617,
  title = {{Lifted Proximal Operator Machines}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4323},
}

@inproceedings{neurips2019_who_59202,
  title = {{Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14568},
}

@inproceedings{neurips2020_agnostic_59356,
  title = {{Agnostic Learning of a Single Neuron with Gradient Descent}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18046},
}

@inproceedings{icml2017_provable_36352,
  title = {{Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/635},
}

@inproceedings{neurips2020_tight_60974,
  title = {{Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17652},
}

@inproceedings{neurips2019_time_59097,
  title = {{Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14566},
}

@inproceedings{neurips2016_globally_55758,
  title = {{Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7131},
}

@inproceedings{icml2023_the_41796,
  title = {{The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24940},
}

@inproceedings{neurips2019_distributed_58153,
  title = {{Distributed Low-rank Matrix Factorization With Exact Consensus}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13905},
}

@inproceedings{icml2020_superpolynomial_38822,
  title = {{Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6700},
}

@inproceedings{iclr2024_on_33813,
  title = {{On the hardness of learning under symmetries}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19262},
}

@inproceedings{icml2024_why_44773,
  title = {{Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33679},
}

@inproceedings{neurips2024_on_72051,
  title = {{On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95269},
}

@inproceedings{neurips2024_improving_72403,
  title = {{Improving Adaptivity via Over-Parameterization in Sequence Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94952},
}

@inproceedings{neurips2024_least_73340,
  title = {{Least Squares Regression Can Exhibit Under-Parameterized Double Descent}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94105},
}

@inproceedings{iclr2024_sgd_34093,
  title = {{SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18982},
}

@inproceedings{iclr2024_symmetric_34839,
  title = {{Symmetric Single Index Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18235},
}

@inproceedings{iclr2024_how_35613,
  title = {{How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17460},
}

@inproceedings{icml2024_symmetric_44557,
  title = {{Symmetric Matrix Completion with ReLU Sampling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33895},
}

@inproceedings{icml2025_mixture_45988,
  title = {{Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46558},
}

@inproceedings{icml2025_learning_47451,
  title = {{Learning Curves of Stochastic Gradient Descent in Kernel Regression}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45142},
}

@inproceedings{icml2025_on_48201,
  title = {{On the Benefits of Active Data Collection in Operator Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44410},
}

@inproceedings{icml2025_optimization_48459,
  title = {{Optimization for Neural Operators can Benefit from Width}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44158},
}

@inproceedings{icml2025_the_48848,
  title = {{The Power of Random Features and the Limits of Distribution-Free Gradient Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43774},
}

@inproceedings{icml2026_data_50139,
  title = {{Data Reconstruction: Identifiability and Optimization with Sample Splitting}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=9LoNh2EZ2g},
}

@inproceedings{icml2026_convex_50805,
  title = {{Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=FtfV0UuRGz},
}

@inproceedings{icml2026_full_51831,
  title = {{Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=QItZDBVCT0},
}

@inproceedings{icml2026_spectral_55026,
  title = {{Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=uyizpRy7kS},
}

@inproceedings{icml2026_joint_55313,
  title = {{Joint Learning in the Gaussian Single Index Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=xf1OYJfvqj},
}

@inproceedings{neurips2024_matching_71211,
  title = {{Matching the Statistical Query Lower Bound for \$k\$-Sparse Parity Problems with Sign Stochastic Gradient Descent}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96024},
}