Skip to content

μLO: Compute-Efficient Meta-Generalization of Learned Optimizers [to appear at ICLR 2026]

Notifications You must be signed in to change notification settings

SamsungSAILMontreal/mulo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 

Repository files navigation

μLO: Compute-Efficient Meta-Generalization of Learned Optimizers

Authors: Benjamin Thérien, Charles-Étienne Joseph, Boris Knyazev, Edouard Oyallon, Irina Rish, Eugene Belilovsky

Official code: https://github.com/bentherien/mu_learned_optimization

Paper (ICLR 2026 version): https://openreview.net/forum?id=f8z2bzOLK2

Previous paper version (Oral at Neurips OPT2024): https://arxiv.org/abs/2406.00153

Related repo for the paper Meta-learning Optimizers for Communication-Efficient Learning [TMLR 2025]: https://github.com/lefameuxbeding/learned_aggregation

About

μLO: Compute-Efficient Meta-Generalization of Learned Optimizers [to appear at ICLR 2026]

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published