Generalizing Adam to Manifolds For Efficiently Training Transformers

Brantner, B.; Kraus, M.

Lokale TagsFreigabegeschichteDetailsÜbersicht

Generalizing Adam to Manifolds For Efficiently Training Transformers

Brantner, B., & Kraus, M. (2023). Generalizing Adam to Manifolds For Efficiently Training Transformers. Talk presented at European Conference on Numerical Mathematics and Advanced Applications (ENUMATH 2023). Lisbon. 2023-09-04 - 2023-09-08.

Item is Freigegeben

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:

Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-000D-B87E-7 Versions-Permalink: https://hdl.handle.net/21.11116/0000-000D-B882-0

Genre: Vortrag

ausblenden:

Urheber:
Brantner, B.^{1, 2}, Autor
Kraus, M.¹, Autor

Affiliations:
1Numerical Methods in Plasma Physics (NMPP), Max Planck Institute for Plasma Physics, Max Planck Society, ou_1856344
2External Organizations, ou_persistent22