Asher Trockman, J. Zico Kolter. Mimetic Initialization of Self-Attention Layers. In Andreas Krause 0001, Emma Brunskill, KyungHyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett, editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA. Volume 202 of Proceedings of Machine Learning Research, pages 34456-34468, PMLR, 2023. [doi]
@inproceedings{TrockmanK23-0,
title = {Mimetic Initialization of Self-Attention Layers},
author = {Asher Trockman and J. Zico Kolter},
year = {2023},
url = {https://proceedings.mlr.press/v202/trockman23a.html},
researchr = {https://researchr.org/publication/TrockmanK23-0},
cites = {0},
citedby = {0},
pages = {34456-34468},
booktitle = {International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA},
editor = {Andreas Krause 0001 and Emma Brunskill and KyungHyun Cho and Barbara Engelhardt and Sivan Sabato and Jonathan Scarlett},
volume = {202},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}