Mert Demirer, Vasilis Syrgkanis, Greg Lewis, Victor Chernozhukov
arXiv 24 May 2019 · Econometrics · 16 citations (OpenAlex)
arXiv:1905.10116 · PDF · DOI · OpenAlex · Extracted main text
We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value function takes a known parametric form in the treatment, but we are agnostic on how it depends on the observed contexts. We propose a doubly robust off-policy estimate for this setting and show that off-policy optimization based on this estimate is robust to estimation errors of the policy function or the regression model. Our results also apply if the model does not satisfy our semi-parametric form, but rather we measure regret in terms of the best projection of the true value function to this functional space. Our work extends prior approaches of policy optimization from observational data that only considered discrete actions. We provide an experimental evaluation of our method in a synthetic data example motivated by optimal personalized pricing and costly resource allocation.
appendix boundary found by appendix_command · 44% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Susan Athey and Stefan Wager (2018) Efficient policy learning | 0.950 | 7 | 3 | 86% |
| 2 | Dylan J Foster and Vasilis Syrgkanis (2019) Orthogonal statistical learning self | 0.714 | 11 | 3 | 36% |
| 3 | Adith Swaminathan and Thorsten Joachims (2015) Counterfactual risk minimization: Learning from logged bandit feedback | 0.693 | 5 | 1 | 100% |
| 4 | Nathan Kallus and Angela Zhou (2018) Policy evaluation and optimization with continuous treatments | 0.644 | 4 | 1 | 100% |
| 5 | Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo,… (2018) Double/debiased machine learning for treatment and structural parameters self | 0.644 | 2 | 2 | 100% |
| 6 | Zhengyuan Zhou, Susan Athey, and Stefan Wager (2018) Offline multi-action policy learning: Generalization and optimization | 0.585 | 3 | 1 | 100% |
| 7 | A. W. Van Der Vaart and J. A. Wellner (1996) Weak Convergence and Empirical Processes: With Applications to Statistics | 0.511 | 2 | 2 | 50% |
| 8 | Bryan S Graham and Cristine Campos de Xavier Pinto (2018) Semiparametrically efficient estimation of the average linear regression function | 0.511 | 2 | 1 | 100% |
| 9 | Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, and Chiche… (2019) Contextual bandits with continuous actions: Smoothing, zooming, and adapting | 0.511 | 2 | 1 | 100% |
| 10 | Martin J. Wainwright (2019) High-Dimensional Statistics: A Non-Asymptotic Viewpoint | 0.511 | 2 | 1 | 100% |
Showing the top 10 of 28 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.