Login / Signup
Efficient GPT Model Pre-training using Tensor Train Matrix Representation.
Viktoria Chekalina
Georgiy Novikov
Julia Gusak
Alexander Panchenko
Ivan V. Oseledets
Published in:
PACLIC (2023)
Keyphrases
</>
probabilistic model
high order
matrix representation
higher order
feature space
missing data
nonnegative matrix factorization