• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Towards Memory-Efficient Training for Extremely Large Output Spaces - Learning with 670k Labels on a Single Commodity GPU.

Erik SchultheisRohit Babbar
Published in: ECML/PKDD (3) (2023)
Keyphrases
  • memory efficient
  • supervised learning
  • single commodity
  • training set
  • software agents