Author of the publication

Attention is not all you need: pure attention loses rank doubly exponentially with depth.

, , and . ICML, volume 139 of Proceedings of Machine Learning Research, page 2793-2803. PMLR, (2021)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

Discriminative structural graph classification., , and . CoRR, (2019)On the Relationship between Self-Attention and Convolutional Layers, , and . (2019)cite arxiv:1911.03584Comment: To appear at ICLR 2020.A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences., , , , , , , , , and 2 other author(s). CoRR, (2022)AbDiffuser: Full-Atom Generation of In-Vitro Functioning Antibodies., , , , , , , , , and 1 other author(s). CoRR, (2023)Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions., , , and . NeurIPS, (2022)How hard is to distinguish graphs with graph neural networks?. NeurIPS, (2020)Predicting the evolution of stationary graph signals., , and . ACSSC, page 60-64. IEEE, (2017)Dynamic Balanced Graph Partitioning., , , , and . SIAM J. Discret. Math., 34 (3): 1791-1812 (2020)On the Relationship between Self-Attention and Convolutional Layers, , and . Inproceedings ICLR 2020, (2020)Towards stationary time-vertex signal processing., , , and . ICASSP, page 3914-3918. IEEE, (2017)