Timezone: »

On Adaptivity and Confounding in Contextual Bandit Experiments
Chao Qin · Daniel Russo

Multi-armed bandit algorithms minimize experimentation costs required to converge on optimal behavior. They do so by rapidly adapting experimentation effort away from poorly performing actions as feedback is observed. But this desirable feature makes them sensitive to confounding. We highlight, for instance, that popular bandit algorithms cannot address the problem of identifying the best action when day-of-week effects may confound inferences. In response, this paper proposes deconfounded Thompson sampling, which makes simple, but critical, modifications to the way Thompson sampling is usually applied. Theoretical guarantees suggest the algorithm strikes a delicate balance between adaptivity and robustness to confounding. It attains asymptotic lower bounds on the number of samples required to confidently identify the best action --- suggesting optimal adaptivity --- but also satisfies strong performance guarantees in the presence of day-of-week effects and delayed observations --- suggesting unusual robustness.

Author Information

Chao Qin (Columbia University)
Daniel Russo (Columbia University)

More from the Same Authors