% Key papers for Stochastic gradient last-iterate analysis (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2017_sgdr_28328,
  title = {{SGDR: Stochastic Gradient Descent with Warm Restarts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=Skq89Scxx},
}

@inproceedings{icml2019_adagrad_37129,
  title = {{AdaGrad Stepsizes: Sharp Convergence Over Nonconvex Landscapes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4063},
}

@inproceedings{neurips2016_stochastic_56010,
  title = {{Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7106},
}

@inproceedings{icml2018_sgd_36969,
  title = {{SGD and Hogwild! Convergence Without the Bounded Gradients Assumption}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2313},
}

@inproceedings{neurips2019_private_58837,
  title = {{Private Stochastic Convex Optimization with Optimal Rates}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14596},
}

@inproceedings{neurips2019_the_59073,
  title = {{The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14405},
}

@inproceedings{icml2016_sdna_35972,
  title = {{SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/qub16.html},
}

@inproceedings{icml2018_on_36884,
  title = {{On Acceleration with Noise-Corrupted Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2173},
}

@inproceedings{icml2018_stochastic_37007,
  title = {{Stochastic Proximal Algorithms for AUC Maximization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1921},
}

@inproceedings{icml2018_fast_36691,
  title = {{Fast Stochastic AUC Maximization with \$O(1/n)\$-Convergence Rate}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1940},
}

@inproceedings{neurips2016_generalization_55748,
  title = {{Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7418},
}

@inproceedings{icml2019_sgd_37712,
  title = {{SGD without Replacement: Sharper Rates for General Smooth Convex Functions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3814},
}

@inproceedings{neurips2018_a_56791,
  title = {{A Block Coordinate Ascent Algorithm for Mean-Variance Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11126},
}

@inproceedings{neurips2019_painless_58786,
  title = {{Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13540},
}

@inproceedings{neurips2017_differentially_56254,
  title = {{Differentially Private Empirical Risk Minimization Revisited: Faster and More General}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9058},
}

@inproceedings{neurips2019_a_57847,
  title = {{A Universally Optimal Multistage Accelerated Stochastic Gradient Method}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13913},
}

@inproceedings{icml2019_anytime_37160,
  title = {{Anytime Online-to-Batch, Optimism and Acceleration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4147},
}

@inproceedings{neurips2020_stability_60861,
  title = {{Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18025},
}

@inproceedings{icml2017_stochastic_36410,
  title = {{Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/886},
}

@inproceedings{icml2018_sadagrad_36966,
  title = {{SADAGRAD: Strongly Adaptive Stochastic Gradient Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2010},
}

@inproceedings{iclr2024_revisiting_35641,
  title = {{Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17432},
}

@inproceedings{icml2024_random_44245,
  title = {{Random Scaling and Momentum for Non-smooth Non-convex Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34207},
}

@inproceedings{icml2024_universal_44601,
  title = {{Universal Gradient Methods for Stochastic Convex Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33851},
}

@inproceedings{neurips2024_stochastic_72431,
  title = {{Stochastic Newton Proximal Extragradient Method}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94925},
}

@inproceedings{neurips2024_stability_72911,
  title = {{Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94500},
}

@inproceedings{iclr2025_nonconvex_81901,
  title = {{Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29883},
}

@inproceedings{icml2024_stochastic_44083,
  title = {{Stochastic Optimization with Arbitrary Recurrent Data Sampling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34369},
}

@inproceedings{icml2024_stability_44634,
  title = {{Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33818},
}

@inproceedings{icml2024_on_44637,
  title = {{On the Last-Iterate Convergence of Shuffling Gradient Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33815},
}

@inproceedings{icml2024_efficient_45368,
  title = {{Efficient Stochastic Approximation of Minimax Excess Risk Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33083},
}

@inproceedings{icml2025_provable_46927,
  title = {{Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45653},
}

@inproceedings{icml2025_clipping_46990,
  title = {{Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45593},
}

@inproceedings{icml2025_incremental_47006,
  title = {{Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45577},
}

@inproceedings{icml2026_bregman_49835,
  title = {{Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete Time}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=69IOkVkTQX},
}

@inproceedings{icml2026_on_52248,
  title = {{On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=U1bxeLQLaK},
}

@inproceedings{icml2026_can_53461,
  title = {{Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=fiYjuwsbFE},
}

@inproceedings{icml2026_stability_53842,
  title = {{Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=jHUEoBLQpn},
}

@inproceedings{icml2026_towards_54884,
  title = {{Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding Analysis}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=tYUt9ffVcD},
}

@inproceedings{icml2026_high_55300,
  title = {{High-Probability Convergence Guarantees of Decentralized SGD}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=xSYhEkiyp5},
}

@inproceedings{neurips2024_near_70747,
  title = {{Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96378},
}