Login / Signup

Efficient GPT Model Pre-training using Tensor Train Matrix Representation.

Viktoria ChekalinaGeorgii S. NovikovJulia GusakIvan V. OseledetsAlexander Panchenko
Published in: CoRR (2023)
Keyphrases
  • high order
  • probabilistic model
  • matrix representation
  • bayesian networks
  • feature space
  • input data