Login / Signup
Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization offers Significant Performance and Efficiency Gains.
Sathya N. Ravi
Abhay Venkatesh
Glenn Moo Fung
Vikas Singh
Published in:
CoRR (2019)
Keyphrases
</>
data dependent
efficiency gains
energy functional
rademacher complexity
significantly higher
reproducing kernel hilbert space
point sets
risk bounds
learning algorithm
computer vision
query processing
knn