Login / Signup
What Algorithms can Transformers Learn? A Study in Length Generalization.
Hattie Zhou
Arwen Bradley
Etai Littwin
Noam Razin
Omid Saremi
Joshua M. Susskind
Samy Bengio
Preetum Nakkiran
Published in:
ICLR (2024)
Keyphrases
</>
learning algorithm
benchmark datasets
empirical studies
orders of magnitude
worst case
times faster
recently developed
efficient learning
neural network
social networks
e learning
data structure
optimization problems
computationally efficient
theoretical framework
classification algorithm