Online gradient descent for least squares regression: Non-asymptotic bounds and application to bandits.

Nathaniel Korda Prashanth L. A.Rémi Munos

Published in: CoRR (2013)

Keyphrases

online learning
lower bound
worst case
real time
cost function
information retrieval
upper bound
application specific
information systems
case study
objective function
sample size
asymptotically optimal