% Key papers for Private online and user-level learning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2016_differential_104993,
  title = {{Differential Privacy Preservation for Deep Auto-Encoders: an Application of Human Behavior Prediction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10165},
}

@inproceedings{neurips2021_remember_63219,
  title = {{Remember What You Want to Forget: Algorithms for Machine Unlearning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26644},
}

@inproceedings{neurips2020_differentially_59701,
  title = {{Differentially-Private Federated Linear Bandits}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16939},
}

@inproceedings{icml2016_efficient_35815,
  title = {{Efficient Private Empirical Risk Minimization for High-dimensional Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/kasiviswanathan16.html},
}

@inproceedings{neurips2019_privacy_58834,
  title = {{Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14123},
}

@inproceedings{icml2019_differentially_37287,
  title = {{Differentially Private Empirical Risk Minimization with Non-convex Loss Functions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3618},
}

@inproceedings{icml2021_the_40014,
  title = {{The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9805},
}

@inproceedings{neurips2016_online_55914,
  title = {{Online and Differentially-Private Tensor Decomposition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/6985},
}

@inproceedings{neurips2018_model_57385,
  title = {{Model-Agnostic Private Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11684},
}

@inproceedings{iclr2020_differentially_29790,
  title = {{Differentially Private Meta-Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rJgqMRVYvr},
}

@inproceedings{icml2016_differentially_35795,
  title = {{Differentially Private Policy Evaluation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/balle16.html},
}

@inproceedings{aaai2017_cleaning_104558,
  title = {{Cleaning the Null Space: A Privacy Mechanism for Predictors}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10935},
}

@inproceedings{icml2019_differentially_37288,
  title = {{Differentially Private Fair Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4111},
}

@inproceedings{neurips2019_differentially_58130,
  title = {{Differentially Private Algorithms for Learning Mixtures of Separated Gaussians}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13262},
}

@inproceedings{aaai2021_local_942,
  title = {{Local Differential Privacy for Bayesian Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/11152-local-differential-privacy-for-bayesian-optimization/},
}

@inproceedings{neurips2019_limits_58549,
  title = {{Limits of Private Learning with Access to Public Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14048},
}

@inproceedings{neurips2020_learning_60212,
  title = {{Learning from Mixtures of Private and Public Populations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17982},
}

@inproceedings{icml2022_the_41247,
  title = {{The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17529},
}

@inproceedings{aaai2018_uplink_100347,
  title = {{Uplink Communication Efficient Differentially Private Sparse Optimization With Feature-Wise Distributed Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11311},
}

@inproceedings{icml2020_data_38076,
  title = {{Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6262},
}

@inproceedings{iclr2024_on_34794,
  title = {{On Differentially Private Federated Linear Contextual Bandits}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18280},
}

@inproceedings{neurips2024_differentially_70428,
  title = {{Differentially Private Optimization with Sparse Gradients}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96677},
}

@inproceedings{neurips2024_the_71094,
  title = {{The Limits of Differential Privacy in Online Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96120},
}

@inproceedings{neurips2024_differentially_72281,
  title = {{Differentially Private Reinforcement Learning with Self-Play}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95064},
}

@inproceedings{iclr2024_tractable_35307,
  title = {{Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17766},
}

@inproceedings{icml2024_auditing_43921,
  title = {{Auditing Private Prediction}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34531},
}

@inproceedings{icml2024_differentially_44071,
  title = {{Differentially Private Post-Processing for Fair Regression}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34381},
}

@inproceedings{icml2025_certification_48968,
  title = {{Certification for Differentially Private Prediction in Gradient-Based Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43655},
}

@inproceedings{neurips2024_differential_71792,
  title = {{Differential Privacy in Scalable General Kernel Learning via \$K\$-means Nystr"om Random Features}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95503},
}

@inproceedings{neurips2025_how_74674,
  title = {{How Well Can Differential Privacy Be Audited in One Run?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=004uTlSufe},
}

@inproceedings{iclr2026_back_85423,
  title = {{Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=EEr6cADbZx},
}

@inproceedings{aaai2025_improving_9538,
  title = {{Improving Private Random Forest Prediction Using Matrix Representation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34289},
}

@inproceedings{iclr2024_learning_33958,
  title = {{Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19117},
}

@inproceedings{icml2024_privately_44256,
  title = {{Privately Learning Smooth Distributions on the Hypercube by Projections}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34196},
}

@inproceedings{icml2024_improved_44548,
  title = {{Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33904},
}

@inproceedings{icml2024_differentially_45179,
  title = {{Differentially Private Decentralized Learning with Random Walks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33273},
}

@inproceedings{icml2024_private_45542,
  title = {{Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32910},
}

@inproceedings{icml2025_a_47626,
  title = {{A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44971},
}

@inproceedings{icml2025_certifiably_47964,
  title = {{Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44641},
}

@inproceedings{icml2025_private_48224,
  title = {{Private Model Personalization Revisited}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44387},
}