Corpus ID: 59316905

Orthogonal Statistical Learning

@article{Foster2019OrthogonalSL,
  title={Orthogonal Statistical Learning},
  author={Dylan J. Foster and Vasilis Syrgkanis},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.09036}
}
  • Dylan J. Foster, Vasilis Syrgkanis
  • Published 2019
  • Computer Science, Mathematics, Economics
  • ArXiv
  • We provide excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target model depends on an unknown model that must be to be estimated from data (a "nuisance model"). We analyze a two-stage sample splitting meta-algorithm that takes as input two arbitrary estimation algorithms: one for the target model and one for the nuisance model. We show that if the population risk satisfies a condition called Neyman orthogonality, the… CONTINUE READING
    Semi-Parametric Efficient Policy Learning with Continuous Actions
    • 14
    • PDF
    Machine Learning Estimation of Heterogeneous Treatment Effects with Instruments
    • 5
    • PDF
    Off-Policy Evaluation and Learning for External Validity under a Covariate Shift
    • 7
    • PDF
    Minimax Estimation of Conditional Moment Models
    • 2
    • PDF
    Statistically Efficient Off-Policy Policy Gradients
    • 4
    • PDF
    De-biased Machine Learning for Compliers
    • 1
    Counterfactual Cross-Validation: Effective Causal Model Selection from Observational Data
    • 1
    Counterfactual Learning of Continuous Stochastic Policies
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 78 REFERENCES
    Improving predictive inference under covariate shift by weighting the log-likelihood function
    • 1,082
    • PDF
    Estimation of Regression Coefficients When Some Regressors are not Always Observed
    • 1,861
    Statistical Learning with Sparsity: The Lasso and Generalizations
    • 782
    • PDF
    Double/Debiased Machine Learning for Treatment and Structural Parameters
    • 361
    • Highly Influential
    • PDF
    The Self-Normalized Estimator for Counterfactual Learning
    • 138
    • PDF
    Semiparametric Efficiency in Multivariate Regression Models with Missing Data
    • 708
    Generalized Random Forests
    • 289
    • PDF
    Domain Adaptation for Statistical Classifiers
    • 764
    • PDF
    Doubly Robust Policy Evaluation and Learning
    • 328
    • Highly Influential
    • PDF
    Counterfactual Risk Minimization: Learning from Logged Bandit Feedback
    • 169
    • PDF