Global Guarantees for Enforcing Deep Generative Priors by Empirical Risk.

Paul Hand Vladislav Voroninski

Published in: COLT (2018)

Keyphrases

empirical risk
loss function
risk minimization
ridge regression
generative model
decision function
prediction error
fixed number
bayesian framework
majority vote
support vector
convex optimization
learning algorithm
prior information
active learning
feature space
uniform convergence
convex optimization problems