Login / Signup
An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling.
Qin Ding
Cho-Jui Hsieh
James Sharpnack
Published in:
AISTATS (2021)
Keyphrases
</>
stochastic gradient descent
cost function
monte carlo
online algorithms
k means
learning algorithm
objective function
worst case
expectation maximization
parameter estimation
generalized linear
posterior probability
convergence rate
closed form
sample size
em algorithm
knn
computer vision