We consider policy optimization in contextual bandits, where one is give...
Many large-scale recommender systems consist of two stages, where the fi...
Many selection processes such as finding patients qualifying for a medic...
Automated decision support systems promise to help human experts solve t...
Contextual bandit algorithms have become widely used for recommendation ...
Ranking items by their probability of relevance has long been the goal o...
Although according to several benchmarks automatic machine reading
compr...
In this technical report, we introduce FastFusionNet, an efficient varia...
The ability to perform offline A/B-testing and off-policy learning using...
Not all people are equally easy to identify: color statistics might be e...