Stochastic Zeroth Order Gradient and Hessian Estimators: Variance Reduction and Refined Bias Bounds.

Yasong Feng Tianyu Wang

Published in: CoRR (2022)

Keyphrases

variance reduction
gradient estimation
monte carlo
bias variance decomposition
sample size
policy gradient
confidence intervals
importance sampling
quasi monte carlo
upper bound
training data
markov random field
naive bayes classifier