Login / Signup

Gradient Sparsification For Masked Fine-Tuning of Transformers.

James O'NeillSourav Dutta
Published in: IJCNN (2023)
Keyphrases
  • fine tuning
  • viable alternative
  • fine tune
  • fine tuned
  • edge detection
  • gradient information
  • least squares
  • special case
  • gradient method
  • real world
  • data mining
  • computer vision
  • support vector
  • steepest ascent