Sequence Length Independent Norm-Based Generalization Bounds for Transformers.

Jacob Trauger Ambuj Tewari

Published in: CoRR (2023)

Keyphrases

generalization bounds
data dependent
generalization ability
learning theory
convex combinations
model selection
ranking algorithm
vc dimension
statistical learning theory
learning problems
ranking functions
linear classifiers
kernel machines
pairwise
learning machines
learning algorithm
machine learning