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]

Authors

Lorenzo Noci

This author has not been identified. Look up 'Lorenzo Noci' in Google

Sotiris Anagnostidis

This author has not been identified. Look up 'Sotiris Anagnostidis' in Google

Luca Biggio

This author has not been identified. Look up 'Luca Biggio' in Google

Antonio Orvieto

This author has not been identified. Look up 'Antonio Orvieto' in Google

Sidak Pal Singh

This author has not been identified. Look up 'Sidak Pal Singh' in Google

Aurélien Lucchi

This author has not been identified. Look up 'Aurélien Lucchi' in Google