Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers.

Jiuxiang Gu Yingyu Liang Zhenmei Shi Zhao Song Yufa Zhou

Published in: CoRR (2024)

Keyphrases

efficient learning
higher order
structured prediction
high order
natural images
pairwise
conditional random fields
database
learning algorithm
database systems
training set
pattern languages
artificial intelligence
lower bound
distributed systems
tree models