% Key papers for Privacy accounting and mechanisms (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2018_improving_36753,
  title = {{Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2245},
}

@inproceedings{neurips2016_privacy_55940,
  title = {{Privacy Odometers and Filters: Pay-as-you-Go Composition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7262},
}

@inproceedings{aaai2017_the_104507,
  title = {{The Bernstein Mechanism: Function Release under Differential Privacy}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10884},
}

@inproceedings{neurips2017_practical_56585,
  title = {{Practical Locally Private Heavy Hitters}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9016},
}

@inproceedings{neurips2018_empirical_57094,
  title = {{Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11117},
}

@inproceedings{neurips2021_the_62756,
  title = {{The Skellam Mechanism for Differentially Private Federated Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27581},
}

@inproceedings{icml2020_new_38508,
  title = {{New Oracle-Efficient Algorithms for Private Synthetic Data Release}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5814},
}

@inproceedings{neurips2020_locally_60264,
  title = {{Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17357},
}

@inproceedings{icml2019_poission_37656,
  title = {{Poission Subsampled Rényi Differential Privacy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4317},
}

@inproceedings{neurips2020_permute_60578,
  title = {{Permute-and-Flip: A new mechanism for differentially private selection}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17066},
}

@inproceedings{neurips2019_practical_58821,
  title = {{Practical Differentially Private Top-k Selection with Pay-what-you-get Composition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14515},
}

@inproceedings{icml2017_differentially_36156,
  title = {{Differentially Private Submodular Maximization: Data Summarization in Disguise}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/637},
}

@inproceedings{icml2020_optimal_38582,
  title = {{Optimal Differential Privacy Composition for Exponential Mechanisms}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6687},
}

@inproceedings{neurips2020_instance_60093,
  title = {{Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18419},
}

@inproceedings{icml2017_pain_36335,
  title = {{Pain-Free Random Differential Privacy with Sensitivity Sampling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/727},
}

@inproceedings{icml2021_differentially_39242,
  title = {{Differentially Private Query Release Through Adaptive Projection}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9359},
}

@inproceedings{neurips2020_the_60943,
  title = {{The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18158},
}

@inproceedings{neurips2019_efficiently_58204,
  title = {{Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13543},
}

@inproceedings{icml2017_differentially_36152,
  title = {{Differentially Private Chi-squared Test by Unit Circle Mechanism}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/847},
}

@inproceedings{neurips2021_iterative_62988,
  title = {{Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27916},
}

@inproceedings{neurips2024_prior_73611,
  title = {{Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93876},
}

@inproceedings{neurips2024_universal_71084,
  title = {{Universal Exact Compression of Differentially Private Mechanisms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96129},
}

@inproceedings{neurips2024_faster_72125,
  title = {{Faster Differentially Private Top-\$k\$ Selection: A Joint Exponential Mechanism with Pruning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95207},
}

@inproceedings{iclr2025_optimality_82934,
  title = {{Optimality of Matrix Mechanism on \$ell\_p^p\$-metric}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28869},
}

@inproceedings{aaai2024_instance_6328,
  title = {{Instance-Wise Laplace Mechanism via Deep Reinforcement Learning (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30506},
}

@inproceedings{icml2024_perturb_43415,
  title = {{Perturb-and-Project: Differentially Private Similarities and Marginals}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35037},
}

@inproceedings{icml2024_individualized_45830,
  title = {{Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32622},
}

@inproceedings{icml2025_distributed_45964,
  title = {{Distributed Differentially Private Data Analytics via Secure Sketching}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46582},
}

@inproceedings{icml2025_differentially_47125,
  title = {{Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45462},
}

@inproceedings{icml2025_auditing_47151,
  title = {{Auditing \$f\$-differential privacy in one run}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45436},
}

@inproceedings{icml2025_on_48350,
  title = {{On Differential Privacy for Adaptively Solving Search Problems via Sketching}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44265},
}

@inproceedings{icml2025_private_48428,
  title = {{Private Lossless Multiple Release}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44189},
}

@inproceedings{icml2025_approximate_49115,
  title = {{Approximate Differential Privacy of the \$ell\_2\$ Mechanism}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43510},
}

@inproceedings{icml2026_asymptotic_50003,
  title = {{Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=82Wosp2Iu1},
}

@inproceedings{icml2026_differentially_50714,
  title = {{Differentially Private Continual Release with Relative Error}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=F5hjwtBmsV},
}

@inproceedings{icml2026_efficient_50944,
  title = {{Efficient privacy loss accounting for subsampling and random allocation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=HDBpda5Vih},
}

@inproceedings{icml2026_persuasive_51665,
  title = {{Persuasive Privacy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=OeY3gcvlvh},
}

@inproceedings{icml2026_mind_51979,
  title = {{Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=RdBsmhb9U7},
}

@inproceedings{icml2026_differentially_52518,
  title = {{Differentially Private Submodular Maximization with a Knapsack Constraint}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Wph27Qttp5},
}

@inproceedings{icml2026_optimal_55100,
  title = {{Optimal conversion from Rényi Differential Privacy to \$f\$-Differential Privacy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=vVoaUGCMGY},
}