Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence.

Ilyas Fatkhullin Niao He

Published in: CoRR (2024)

Keyphrases

bregman divergences
special case
cost sensitive
mahalanobis distance
theoretical guarantees
objective function
kl divergence
learning algorithm
active learning
maximum likelihood
markov chain
loss function
euclidean distance
information theoretic
learning theory
kullback leibler divergence