IDEAS home Printed from https://ideas.repec.org/p/arx/papers/1901.09036.html
   My bibliography  Save this paper

Orthogonal Statistical Learning

Author

Listed:
  • Dylan J. Foster
  • Vasilis Syrgkanis

Abstract

We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data. We analyze a two-stage sample splitting meta-algorithm that takes as input two arbitrary estimation algorithms: one for the target parameter and one for the nuisance parameter. We show that if the population risk satisfies a condition called Neyman orthogonality, the impact of the nuisance estimation error on the excess risk bound achieved by the meta-algorithm is of second order. Our theorem is agnostic to the particular algorithms used for the target and nuisance and only makes an assumption on their individual performance. This enables the use of a plethora of existing results from statistical learning and machine learning to give new guarantees for learning with a nuisance component. Moreover, by focusing on excess risk rather than parameter estimation, we can give guarantees under weaker assumptions than in previous works and accommodate settings in which the target parameter belongs to a complex nonparametric class. We provide conditions on the metric entropy of the nuisance and target classes such that oracle rates---rates of the same order as if we knew the nuisance parameter---are achieved. We also derive new rates for specific estimation algorithms such as variance-penalized empirical risk minimization, neural network estimation and sparse high-dimensional linear model estimation. We highlight the applicability of our results in four settings of central importance: 1) heterogeneous treatment effect estimation, 2) offline policy optimization, 3) domain adaptation, and 4) learning with missing data.

Suggested Citation

  • Dylan J. Foster & Vasilis Syrgkanis, 2019. "Orthogonal Statistical Learning," Papers 1901.09036, arXiv.org, revised Sep 2020.
  • Handle: RePEc:arx:papers:1901.09036
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/1901.09036
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yingqi Zhao & Donglin Zeng & A. John Rush & Michael R. Kosorok, 2012. "Estimating Individualized Treatment Rules Using Outcome Weighted Learning," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 107(499), pages 1106-1118, September.
    2. Robinson, Peter M, 1988. "Root- N-Consistent Semiparametric Regression," Econometrica, Econometric Society, vol. 56(4), pages 931-954, July.
    3. Lester Mackey & Vasilis Syrgkanis & Ilias Zadik, 2017. "Orthogonal Machine Learning: Power and Limitations," Papers 1711.00342, arXiv.org, revised Aug 2018.
    4. Miruna Oprescu & Vasilis Syrgkanis & Zhiwei Steven Wu, 2018. "Orthogonal Random Forest for Causal Inference," Papers 1806.03467, arXiv.org, revised Sep 2019.
    5. Xin Zhou & Nicole Mayer-Hamblett & Umer Khan & Michael R. Kosorok, 2017. "Residual Weighted Learning for Estimating Individualized Treatment Rules," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 112(517), pages 169-187, January.
    6. Denis Nekipelov & Vira Semenova & Vasilis Syrgkanis, 2018. "Regularized Orthogonal Machine Learning for Nonlinear Semiparametric Models," Papers 1806.04823, arXiv.org, revised Oct 2020.
    7. Max H. Farrell & Tengyuan Liang & Sanjog Misra, 2018. "Deep Neural Networks for Estimation and Inference," Papers 1809.09953, arXiv.org, revised Sep 2019.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Mert Demirer & Vasilis Syrgkanis & Greg Lewis & Victor Chernozhukov, 2019. "Semi-Parametric Efficient Policy Learning with Continuous Actions," CeMMAP working papers CWP34/19, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    2. Q. Clairon & R. Henderson & N. J. Young & E. D. Wilson & C. J. Taylor, 2021. "Adaptive treatment and robust control," Biometrics, The International Biometric Society, vol. 77(1), pages 223-236, March.
    3. Martin Huber, 2019. "An introduction to flexible methods for policy evaluation," Papers 1910.00641, arXiv.org.
    4. Khashayar Khosravi & Greg Lewis & Vasilis Syrgkanis, 2019. "Non-Parametric Inference Adaptive to Intrinsic Dimension," Papers 1901.03719, arXiv.org, revised Jun 2019.
    5. Kyle Colangelo & Ying-Ying Lee, 2019. "Double debiased machine learning nonparametric inference with continuous treatments," CeMMAP working papers CWP54/19, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    6. Zhou, Zhengyuan & Athey, Susan & Wager, Stefan, 2018. "Offline Multi-Action Policy Learning: Generalization and Optimization," Research Papers 3734, Stanford University, Graduate School of Business.
    7. Crystal T. Nguyen & Daniel J. Luckett & Anna R. Kahkoska & Grace E. Shearrer & Donna Spruijt‐Metz & Jaimie N. Davis & Michael R. Kosorok, 2020. "Estimating individualized treatment regimes from crossover designs," Biometrics, The International Biometric Society, vol. 76(3), pages 778-788, September.
    8. Yiyan Huang & Cheuk Hang Leung & Xing Yan & Qi Wu & Nanbo Peng & Dongdong Wang & Zhixiang Huang, 2020. "The Causal Learning of Retail Delinquency," Papers 2012.09448, arXiv.org.
    9. Krikamol Muandet & Wittawat Jitkrittum & Jonas Kubler, 2020. "Kernel Conditional Moment Test via Maximum Moment Restriction," Papers 2002.09225, arXiv.org, revised Jun 2020.
    10. Qian Guan & Eric B. Laber & Brian J. Reich, 2016. "Comment," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 111(515), pages 936-942, July.
    11. Zhang, Haixiang & Huang, Jian & Sun, Liuquan, 2020. "A rank-based approach to estimating monotone individualized two treatment regimes," Computational Statistics & Data Analysis, Elsevier, vol. 151(C).
    12. Kyle Colangelo & Ying-Ying Lee, 2020. "Double Debiased Machine Learning Nonparametric Inference with Continuous Treatments," Papers 2004.03036, arXiv.org, revised Oct 2020.
    13. Knaus, Michael C. & Lechner, Michael & Strittmatter, Anthony, 2018. "Machine Learning Estimation of Heterogeneous Causal Effects: Empirical Monte Carlo Evidence," IZA Discussion Papers 12039, Institute of Labor Economics (IZA).
    14. Davide Viviano, 2019. "Policy Targeting under Network Interference," Papers 1906.10258, arXiv.org, revised Mar 2021.
    15. Guanhua Chen & Donglin Zeng & Michael R. Kosorok, 2016. "Personalized Dose Finding Using Outcome Weighted Learning," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 111(516), pages 1509-1521, October.
    16. Jingxiang Chen & Haoda Fu & Xuanyao He & Michael R. Kosorok & Yufeng Liu, 2018. "Estimating individualized treatment rules for ordinal treatments," Biometrics, The International Biometric Society, vol. 74(3), pages 924-933, September.
    17. Sookyo Jeong & Hongseok Namkoong, 2020. "Robust Causal Inference Under Covariate Shift via Worst-Case Subpopulation Treatment Effects," Papers 2007.02411, arXiv.org, revised Jul 2020.
    18. Xinyang Huang & Jin Xu, 2020. "Estimating individualized treatment rules with risk constraint," Biometrics, The International Biometric Society, vol. 76(4), pages 1310-1318, December.
    19. Andrew Bennett & Nathan Kallus, 2020. "Efficient Policy Learning from Surrogate-Loss Classification Reductions," Papers 2002.05153, arXiv.org.
    20. Yanqing Wang & Ying‐Qi Zhao & Yingye Zheng, 2020. "Learning‐based biomarker‐assisted rules for optimized clinical benefit under a risk constraint," Biometrics, The International Biometric Society, vol. 76(3), pages 853-862, September.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:1901.09036. See general information about how to correct material in RePEc.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (arXiv administrators). General contact details of provider: http://arxiv.org/ .

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service hosted by the Research Division of the Federal Reserve Bank of St. Louis . RePEc uses bibliographic data supplied by the respective publishers.