Emmanuel Abbe, Samy Bengio, Enric Boix-Adserà , Etai Littwin, Joshua M. Susskind. Transformers learn through gradual rank increase. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]
@inproceedings{AbbeBBLS23,
title = {Transformers learn through gradual rank increase},
author = {Emmanuel Abbe and Samy Bengio and Enric Boix-Adserà and Etai Littwin and Joshua M. Susskind},
year = {2023},
url = {http://papers.nips.cc/paper_files/paper/2023/hash/4d69c1c057a8bd570ba4a7b71aae8331-Abstract-Conference.html},
researchr = {https://researchr.org/publication/AbbeBBLS23},
cites = {0},
citedby = {0},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}