Aggregated predictors are obtained by making a set of basic predictors vote according to
some weights, that is, to some probability distribution. Randomized predictors are obtained …

Short-and long-term outcomes of an algorithm often differ, with damaging downstream
effects. A known example is a click-bait algorithm, which may increase short-term clicks but …

We consider offline policy optimization (OPO) in contextual bandits, where one is given a
fixed dataset of logged interactions. While pessimistic regularizers are typically used to …

In this paper, we study the problem of estimator selection and hyper-parameter tuning in off-
policy evaluation. Although cross-validation is the most popular method for model selection …

Off-policy learning (OPL) often involves minimizing a risk estimator based on importance
weighting to correct bias from the logging policy used to collect data. However, this method …

The introduction of A/B Testing represented a great leap forward in recommender systems
research. Like the randomized control trial for evaluating drug efficacy; A/B Testing has …

An increasingly important building block of large scale machine learning systems is based
on returning slates; an ordered lists of items given a query. Applications of this technology …

In interactive systems, actions are often correlated, presenting an opportunity for more
sample-efficient off-policy evaluation (OPE) and learning (OPL) in large action spaces. We …

This work investigates the offline formulation of the contextual bandit problem, where the
goal is to leverage past interactions collected under a behavior policy to evaluate, select …

Applied recommender systems research is in a curious position. While there is a very
rigorous protocol for measuring performance by A/B testing, best practice for finding aB'to …