Login / Signup

Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization.

Akhil KediaSai Chetan ChinthakindiWonho Ryu
Published in: EMNLP (Findings) (2021)
Keyphrases
  • dot product
  • objective function
  • gaussian kernels
  • similarity function
  • learning algorithm
  • multiscale
  • feature space