Timezone: »

Conformal Off-Policy Prediction in Contextual Bandits
Muhammad Faaiz Taufiq · Jean-Francois Ton · Rob Cornish · Yee Whye Teh · Arnaud Doucet

Tue Dec 06 09:00 AM -- 11:00 AM (PST) @

Most off-policy evaluation methods for contextual bandits have focused on the expected outcome of a policy, which is estimated via methods that at best provide only asymptotic guarantees. However, in many applications, the expectation may not be the best measure of performance as it does not capture the variability of the outcome. In addition, particularly in safety-critical settings, stronger guarantees than asymptotic correctness may be required. To address these limitations, we consider a novel application of conformal prediction to contextual bandits. Given data collected under a behavioral policy, we propose \emph{conformal off-policy prediction} (COPP), which can output reliable predictive intervals for the outcome under a new target policy. We provide theoretical finite-sample guarantees without making any additional assumptions beyond the standard contextual bandit setup, and empirically demonstrate the utility of COPP compared with existing methods on synthetic and real-world data.

Author Information

Muhammad Faaiz Taufiq (University of Oxford)
Jean-Francois Ton (Bytedance)
Rob Cornish (University of Oxford)
Yee Whye Teh (University of Oxford, DeepMind)

I am a Professor of Statistical Machine Learning at the Department of Statistics, University of Oxford and a Research Scientist at DeepMind. I am also an Alan Turing Institute Fellow and a European Research Council Consolidator Fellow. I obtained my Ph.D. at the University of Toronto (working with Geoffrey Hinton), and did postdoctoral work at the University of California at Berkeley (with Michael Jordan) and National University of Singapore (as Lee Kuan Yew Postdoctoral Fellow). I was a Lecturer then a Reader at the Gatsby Computational Neuroscience Unit, UCL, and a tutorial fellow at University College Oxford, prior to my current appointment. I am interested in the statistical and computational foundations of intelligence, and works on scalable machine learning, probabilistic models, Bayesian nonparametrics and deep learning. I was programme co-chair of ICML 2017 and AISTATS 2010.

Arnaud Doucet (Oxford)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors