3 papers
cs.LG2021
Adapting to Misspecification in Contextual Bandits with Offline Regression Oracles
Sanath Kumar Krishnamurthy, Vitor Hadad, Susan Athey
Computationally efficient contextual bandits are often based on estimating a predictive model of rewards given contexts and arms using past data. However, when the reward model is…
cs.LG2020
Tractable contextual bandits beyond realizability
Sanath Kumar Krishnamurthy, Vitor Hadad, Susan Athey
Tractable contextual bandit algorithms often rely on the realizability assumption - i.e., that the true expected reward model belongs to a known class, such as linear functions. In…
stat.ML2019
Confidence Intervals for Policy Evaluation in Adaptive Experiments
Vitor Hadad, David A. Hirshberg, Ruohan Zhan +2
Adaptive experiment designs can dramatically improve statistical efficiency in randomized trials, but they also complicate statistical inference. For example, it is now well known…