Empirical Inference
Conference Paper
2022
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse
arXiv
| Author(s): | Noci*, L. and Sotiris*, A. and Biggio*, L. and Orvieto*, A. and Singh*, S. P. and Lucchi, A. |
| Links: | |
| Book Title: | Advances in Neural Information Processing Systems 35 (NeurIPS 2022) |
| Volume: | 35 |
| Pages: | 27198--27211 |
| Year: | 2022 |
| Month: | December |
| Editors: | S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh |
| Publisher: | Curran Associates, Inc. |
| BibTeX Type: | Conference Paper (conference) |
| Event Name: | 36th Annual Conference on Neural Information Processing Systems |
| Event Place: | New Orleans Convention Center |
| State: | Published |
| URL: | https://proceedings.neurips.cc/paper_files/paper/2022/hash/ae0cba715b60c4052359b3d52a2cff7f-Abstract-Conference.html |
| Electronic Archiving: | grant_archive |
| Note: | *equal contribution |
| Supplement: | https://proceedings.neurips.cc/paper_files/paper/2022/file/ae0cba715b60c4052359b3d52a2cff7f-Supplemental-Conference.pdf |
BibTeX
@conference{Nocietal22,
title = {Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse},
booktitle = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)},
volume = {35},
pages = {27198--27211},
editors = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
publisher = {Curran Associates, Inc.},
month = dec,
year = {2022},
note = {*equal contribution},
author = {Noci*, L. and Sotiris*, A. and Biggio*, L. and Orvieto*, A. and Singh*, S. P. and Lucchi, A.},
url = {https://proceedings.neurips.cc/paper_files/paper/2022/hash/ae0cba715b60c4052359b3d52a2cff7f-Abstract-Conference.html},
month_numeric = {12}
}