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

@inproceedings{iclr2019_rethinking_29167,
  title = {{Rethinking the Value of Network Pruning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/877},
}

@inproceedings{iclr2020_picking_29681,
  title = {{Picking Winning Tickets Before Training by Preserving Gradient Flow}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=SkgsACVKPH},
}

@inproceedings{neurips2020_pruning_60646,
  title = {{Pruning neural networks without any data by iteratively conserving synaptic flow}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18364},
}

@inproceedings{cvpr2022_how_19012,
  title = {{How Well Do Sparse ImageNet Models Transfer?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{icml2020_dropnet_38134,
  title = {{DropNet: Reducing Neural Network Complexity via Iterative Pruning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6092},
}

@inproceedings{neurips2020_sanity_60780,
  title = {{Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16835},
}

@inproceedings{neurips2021_sparse_62005,
  title = {{Sparse Training via Boosting Pruning Plasticity with Neuroregeneration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28458},
}

@inproceedings{cvpr2024_finding_23470,
  title = {{Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31077},
}

@inproceedings{iclr2022_sparsity_31294,
  title = {{Sparsity Winning Twice: Better Robust Generalization from More Efficient Training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6147},
}

@inproceedings{icml2022_sparse_41189,
  title = {{Sparse Double Descent: Where Network Pruning Aggravates Overfitting}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17249},
}

@inproceedings{icml2023_why_42594,
  title = {{Why Random Pruning Is All We Need to Start Sparse}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24666},
}

@inproceedings{neurips2021_a_62509,
  title = {{A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26319},
}

@inproceedings{neurips2022_lottery_64882,
  title = {{Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53030},
}

@inproceedings{iclr2022_signing_31506,
  title = {{Signing the Supermask: Keep, Hide, Invert}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6550},
}

@inproceedings{icml2022_training_41285,
  title = {{Training Your Sparse Neural Network Better with Any Mask}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16915},
}

@inproceedings{icml2022_winning_41359,
  title = {{Winning the Lottery Ahead of Time: Efficient Early Network Pruning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17709},
}

@inproceedings{icml2024_no_44524,
  title = {{No Free Prune: Information-Theoretic Barriers to Pruning at Initialization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33928},
}

@inproceedings{neurips2020_greedy_59973,
  title = {{Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18430},
}

@inproceedings{iclr2024_sparse_34640,
  title = {{Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18434},
}

@inproceedings{icml2020_dessilbi_38101,
  title = {{DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6087},
}

@inproceedings{iclr2024_masks_35339,
  title = {{Masks, Signs, And Learning Rate Rewinding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17734},
}