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:
AAAI (2020)
Keyphrases
</>
data dependent
efficiency gains
energy functional
rademacher complexity
risk bounds
image segmentation
image processing
kernel methods
hash functions