Login / Signup
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy.
Gintare Karolina Dziugaite
Daniel M. Roy
Published in:
CoRR (2017)
Keyphrases
</>
pac bayes
data dependent
risk bounds
differential privacy
generalization bounds
privacy preserving
empirical risk minimization
uniform convergence
hash functions
energy functional
machine learning
knn
prior information
reproducing kernel hilbert space
stochastic processes