Selecting Observations against Adversarial Objectives
Krause, Andreas, Mcmahan, Brendan, Guestrin, Carlos, Gupta, Anupam
–Neural Information Processing Systems
In many applications, one has to actively select among a set of expensive observations beforemaking an informed decision. Often, we want to select observations which perform well when evaluated with an objective function chosen by an adversary.
Neural Information Processing Systems
Dec-31-2008