references.bib

@inproceedings{yolo,
  title={You only look once: Unified, real-time object detection},
  author={Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={779--788},
  year={2016}
}

@article{vit,
  title={An image is worth 16x16 words: Transformers for image recognition at scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and others},
  journal={arXiv preprint arXiv:2010.11929},
  year={2020}
}

@article{bert,
  title={Bert: Pre-training of deep bidirectional transformers for language understanding},
  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  journal={arXiv preprint arXiv:1810.04805},
  year={2018}
}

@article{gpt3,
  title={Language models are few-shot learners},
  author={Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
  journal={Advances in neural information processing systems},
  volume={33},
  pages={1877--1901},
  year={2020}
}

@article{mobilenet,
  title={Mobilenets: Efficient convolutional neural networks for mobile vision applications},
  author={Howard, Andrew G and Zhu, Menglong and Chen, Bo and Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and Andreetto, Marco and Adam, Hartwig},
  journal={arXiv preprint arXiv:1704.04861},
  year={2017}
}

@article{squeezenet,
  title={SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size},
  author={Iandola, Forrest N and Han, Song and Moskewicz, Matthew W and Ashraf, Khalid and Dally, William J and Keutzer, Kurt},
  journal={arXiv preprint arXiv:1602.07360},
  year={2016}
}

@article{LTH,
  title={The lottery ticket hypothesis: Finding sparse, trainable neural networks},
  author={Frankle, Jonathan and Carbin, Michael},
  journal={arXiv preprint arXiv:1803.03635},
  year={2018}
}

@article{sparsitymaycry,
  title={Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!},
  author={Liu, Shiwei and Chen, Tianlong and Zhang, Zhenyu and Chen, Xuxi and Huang, Tianjin and Jaiswal, Ajay and Wang, Zhangyang},
  journal={arXiv preprint arXiv:2303.02141},
  year={2023}
}

@article{PIE,
  title={What do compressed deep neural networks forget?},
  author={Hooker, Sara and Courville, Aaron and Clark, Gregory and Dauphin, Yann and Frome, Andrea},
  journal={arXiv preprint arXiv:1911.05248},
  year={2019}
}

@article{liu2018rethinking,
  title={Rethinking the value of network pruning},
  author={Liu, Zhuang and Sun, Mingjie and Zhou, Tinghui and Huang, Gao and Darrell, Trevor},
  journal={arXiv preprint arXiv:1810.05270},
  year={2018}
}

@article{jaiswal2023emergence,
  title={The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter},
  author={Jaiswal, Ajay and Liu, Shiwei and Chen, Tianlong and Wang, Zhangyang},
  journal={arXiv preprint arXiv:2306.03805},
  year={2023}
}

@article{GPT4,
  title={GPT-4 Technical Report},
  author={OpenAI},
  journal={ArXiv},
  year={2023},
  volume={abs/2303.08774}
}

@article{hinton2022forward,
  title={The forward-forward algorithm: Some preliminary investigations},
  author={Hinton, Geoffrey},
  journal={arXiv preprint arXiv:2212.13345},
  year={2022}
}

@article{redunet,
  title={ReduNet: A white-box deep network from the principle of maximizing rate reduction},
  author={Chan, Kwan Ho Ryan and Yu, Yaodong and You, Chong and Qi, Haozhi and Wright, John and Ma, Yi},
  journal={The Journal of Machine Learning Research},
  volume={23},
  number={1},
  pages={4907--5009},
  year={2022},
  publisher={JMLRORG}
}

@article{morcos2019one,
  title={One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers},
  author={Morcos, Ari and Yu, Haonan and Paganini, Michela and Tian, Yuandong},
  journal={Advances in neural information processing systems},
  volume={32},
  year={2019}
}


@InProceedings{pmlr-v139-liu21aa,
  title = 	 {Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?},
  author =       {Liu, Ning and Yuan, Geng and Che, Zhengping and Shen, Xuan and Ma, Xiaolong and Jin, Qing and Ren, Jian and Tang, Jian and Liu, Sijia and Wang, Yanzhi},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {7011--7020},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR}, 
}

@inproceedings{sparsedoubledescent,
  title={Sparse Double Descent: Where Network Pruning Aggravates Overfitting},
  author={He, Zheng and Xie, Zeke and Zhu, Quanzhi and Qin, Zengchang},
  booktitle={International Conference on Machine Learning},
  pages={8635--8659},
  year={2022},
  organization={PMLR}
}

@article{liebenwein2021lost,
  title={Lost in pruning: The effects of pruning neural networks beyond test accuracy},
  author={Liebenwein, Lucas and Baykal, Cenk and Carter, Brandon and Gifford, David and Rus, Daniela},
  journal={Proceedings of Machine Learning and Systems},
  volume={3},
  pages={93--138},
  year={2021}
}

@inproceedings{NEURIPS2020_b6af2c97,
 author = {Chen, Tianlong and Frankle, Jonathan and Chang, Shiyu and Liu, Sijia and Zhang, Yang and Wang, Zhangyang and Carbin, Michael},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {15834--15846},
 publisher = {Curran Associates, Inc.},
 title = {The Lottery Ticket Hypothesis for Pre-trained BERT Networks},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/b6af2c9703f203a2794be03d443af2e3-Paper.pdf},
 volume = {33},
 year = {2020}
}

@inproceedings{girish2021lottery,
  title={The lottery ticket hypothesis for object recognition},
  author={Girish, Sharath and Maiya, Shishira R and Gupta, Kamal and Chen, Hao and Davis, Larry S and Shrivastava, Abhinav},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={762--771},
  year={2021}
}

@inproceedings{chen2021lottery,
  title={The lottery tickets hypothesis for supervised and self-supervised pre-training in computer vision models},
  author={Chen, Tianlong and Frankle, Jonathan and Chang, Shiyu and Liu, Sijia and Zhang, Yang and Carbin, Michael and Wang, Zhangyang},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={16306--16316},
  year={2021}
}

@article{DualLTH,
  title={Dual lottery ticket hypothesis},
  author={Bai, Yue and Wang, Huan and Tao, Zhiqiang and Li, Kunpeng and Fu, Yun},
  journal={arXiv preprint arXiv:2203.04248},
  year={2022}
}

@article{yu2023white,
  title={White-Box Transformers via Sparse Rate Reduction},
  author={Yu, Yaodong and Buchanan, Sam and Pai, Druv and Chu, Tianzhe and Wu, Ziyang and Tong, Shengbang and Haeffele, Benjamin D and Ma, Yi},
  journal={arXiv preprint arXiv:2306.01129},
  year={2023}
}

@article{saukh2023representing,
  title={Representing Input Transformations by Low-Dimensional Parameter Subspaces},
  author={Saukh, Olga and Wang, Dong and He, Xiaoxi and Thiele, Lothar},
  journal={arXiv preprint arXiv:2305.13536},
  year={2023}
}