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

@inproceedings{neurips2016_learning_55815,
  title = {{Learning Deep Embeddings with Histogram Loss}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7358},
}

@inproceedings{icml2018_deep_36621,
  title = {{Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1993},
}

@inproceedings{cvpr2020_learning_15805,
  title = {{Learning to Autofocus}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{iclr2019_neural_28855,
  title = {{Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/909},
}

@inproceedings{iclr2019_on_28908,
  title = {{On the loss landscape of a class of deep neural networks with no bad local valleys}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/766},
}

@inproceedings{iclr2018_global_28439,
  title = {{Global Optimality Conditions for Deep Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/90},
}

@inproceedings{icml2018_understanding_37068,
  title = {{Understanding the Loss Surface of Neural Networks for Binary Classification}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2237},
}

@inproceedings{neurips2018_adding_56843,
  title = {{Adding One Neuron Can Eliminate All Bad Local Minima}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11430},
}

@inproceedings{neurips2019_large_58459,
  title = {{Large Scale Structure of Neural Network Loss Landscapes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13777},
}

@inproceedings{iclr2018_critical_28648,
  title = {{Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/169},
}

@inproceedings{iclr2019_small_29175,
  title = {{Small nonlinearities in activation functions create bad local minima in neural networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/808},
}

@inproceedings{iclr2019_conditional_29210,
  title = {{Conditional Network Embeddings}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/812},
}

@inproceedings{aaai2019_the_101545,
  title = {{The Goldilocks Zone: Towards Better Understanding of Neural Network Loss Landscapes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4237},
}

@inproceedings{aaai2020_stochastic_102063,
  title = {{Stochastic Loss Function}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5925},
}

@inproceedings{iclr2018_searnn_28537,
  title = {{SEARNN: Training RNNs with global-local losses}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/191},
}

@inproceedings{iclr2022_critical_30830,
  title = {{Critical Points in Quantum Generative Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6777},
}

@inproceedings{icml2018_the_37040,
  title = {{The Multilinear Structure of ReLU Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2005},
}

@inproceedings{cvpr2025_hotspot_26529,
  title = {{HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32872},
}

@inproceedings{neurips2020_coresets_59605,
  title = {{Coresets for Near-Convex Functions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/19039},
}

@inproceedings{cvpr2022_a_18220,
  title = {{A Unified Framework for Implicit Sinkhorn Differentiation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2024_zipfian_73936,
  title = {{Zipfian Whitening}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93576},
}

@inproceedings{cvpr2024_task_24964,
  title = {{Task-Driven Wavelets using Constrained Empirical Risk Minimization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30226},
}

@inproceedings{iclr2024_mean_34676,
  title = {{Mean Field Theory in Deep Metric Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18398},
}

@inproceedings{aaai2025_set_10752,
  title = {{Set-Valued Sensitivity Analysis of Deep Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35430},
}

@inproceedings{iclr2024_deep_35152,
  title = {{Deep Neural Networks Tend To Extrapolate Predictably}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17921},
}

@inproceedings{icml2025_making_48427,
  title = {{Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44190},
}

@inproceedings{icml2026_deep_52797,
  title = {{Deep Flow Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Z7rhDaBvBo},
}

@inproceedings{icml2026_floating_53506,
  title = {{Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=g89qqA6qmD},
}

@inproceedings{neurips2024_polyhedral_72622,
  title = {{Polyhedral Complex Derivation from Piecewise Trilinear Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94757},
}

@inproceedings{neurips2025_error_76373,
  title = {{Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=IZ1KYTU9ON},
}

@inproceedings{iclr2025_elliptic_82557,
  title = {{Elliptic Loss Regularization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29240},
}

@inproceedings{icml2024_neuro_44643,
  title = {{Neuro-Visualizer: A Novel Auto-Encoder-Based Loss Landscape Visualization Method With an Application in Knowledge-Guided Machine Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33809},
}

@inproceedings{icml2024_monotone_45214,
  title = {{Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33238},
}

@inproceedings{icml2025_a_47862,
  title = {{A Machine Learning Approach to Duality in Statistical Physics}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44740},
}

@inproceedings{iclr2026_memorization_88146,
  title = {{Memorization Through the Lens of Sample Gradients}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=jeTiBeW3iZ},
}

@inproceedings{neurips2026_a_90438,
  title = {{A Surrogate Perspective on Convergence of Fixed-Target DQN}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/155836},
}

@inproceedings{neurips2026_a_92798,
  title = {{A method to automatically discover symbolic local learning rules}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/150193},
}