Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse

Lorenzo Noci, Sotiris Anagnostidis, Luca Biggio, Antonio Orvieto, Sidak Pal Singh, Aurélien Lucchi. Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022. 2022. [doi]

@inproceedings{NociABOSL22,
  title = {Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse},
  author = {Lorenzo Noci and Sotiris Anagnostidis and Luca Biggio and Antonio Orvieto and Sidak Pal Singh and Aurélien Lucchi},
  year = {2022},
  url = {http://papers.nips.cc/paper_files/paper/2022/hash/ae0cba715b60c4052359b3d52a2cff7f-Abstract-Conference.html},
  researchr = {https://researchr.org/publication/NociABOSL22},
  cites = {0},
  citedby = {0},
  booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022},
  editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh},
  isbn = {9781713871088},
}