Generalizing Adam to Manifolds For Efficiently Training Transformers

Brantner, B.; Kraus, M.

Local TagsRelease HistoryDetailsSummary

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 Released

show all hide all

Basic

show hide

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

Genre: Talk

Files

show Files

Locators

show

Creators

show

hide

Creators:
Brantner, B.^{1, 2}, Author
Kraus, M.¹, Author

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

Content

show

Details

show

hide

Language(s): eng - English

Dates: Submitted: 2023

Publication Status: Submitted

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: -

Degree: -

Event

show

hide

Title: European Conference on Numerical Mathematics and Advanced Applications (ENUMATH 2023)

Place of Event: Lisbon

Start-/End Date: 2023-09-04 - 2023-09-08

Legal Case

show

Project information

show

Source

show