Login / Signup
On the Convergence Rate of the Stochastic Gradient Descent (SGD) and application to a modified policy gradient for the Multi Armed Bandit.
Stefana Anita
Gabriel Turinici
Published in:
CoRR (2024)
Keyphrases
</>
stochastic gradient descent
step size
convergence rate
convergence speed
gradient method
learning rate
weight vector
loss function
matrix factorization
least squares
cost function
maximum likelihood
collaborative filtering
random forests
regularization parameter
online algorithms
dynamic programming