Login / Signup
Batch learning from logged bandit feedback through counterfactual risk minimization.
Adith Swaminathan
Thorsten Joachims
Published in:
J. Mach. Learn. Res. (2015)
Keyphrases
</>
risk minimization
batch learning
incremental learning
loss function
empirical risk
generalization error
confidence weighted
concept drift
line search
uniform convergence
multi category
training data
data sets
decision trees
image analysis
image registration