Privacy Amplification via Shuffling for Linear Contextual Bandits.

Evrard Garcelon Kamalika Chaudhuri Vianney Perchet Matteo Pirotta

Published in: CoRR (2021)

Keyphrases

learning algorithm
contextual information
privacy preserving
reinforcement learning
privacy preserving data mining
context sensitive
personal information
linear model
privacy aware
decision trees
lower bound
information loss
security issues
security risks