19 citations · 25 across the 2 of their papers we have counts for
2 papers
stat.ML2017★ 6 cited
Counterfactual Learning for Machine Translation: Degeneracies and Solutions
Carolin Lawrence, Pratik Gajane, Stefan Riezler
Counterfactual learning is a natural scenario to improve web-based machine translation services by offline learning from feedback logged during user interactions. In order to avoid…
cs.LG2017★ 19 cited
Corrupt Bandits for Preserving Local Privacy
Pratik Gajane, Tanguy Urvoy, Emilie Kaufmann
We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preservation in online recommender…