no code implementations • 17 Mar 2015 • Gergely Neu, Gábor Bartók
We propose a sample-efficient alternative for importance weighting for situations where one only has sample access to the probability distribution that generates the observations.
no code implementations • NeurIPS 2014 • Hastagiri P. Vanchinathan, Gábor Bartók, Andreas Krause
In every round, the learner suffers some loss and receives some feedback based on the action and the outcome.
no code implementations • 10 Feb 2014 • Adish Singla, Ilija Bogunovic, Gábor Bartók, Amin Karbasi, Andreas Krause
How should we present training examples to learners to teach them classification rules?
no code implementations • 13 May 2013 • Gergely Neu, Gábor Bartók
We consider the problem of online combinatorial optimization under semi-bandit feedback.