Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach.

Nadav Hallak Panayotis Mertikopoulos Volkan Cevher

Published in: ICML (2021)

Keyphrases

online learning
learning problems
learning algorithm
reinforcement learning
learning process
prior knowledge
inductive learning
neural network
artificial intelligence
active learning
special case
edge detection
learning systems
learning tasks
learning automata