تقرير
A Simple and General Debiased Machine Learning Theorem with Finite Sample Guarantees
| العنوان: | A Simple and General Debiased Machine Learning Theorem with Finite Sample Guarantees |
|---|---|
| المؤلفون: | Chernozhukov, Victor, Newey, Whitney K., Singh, Rahul |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science Mathematics Statistics |
| مصطلحات موضوعية: | Statistics - Machine Learning, Computer Science - Machine Learning, Economics - Econometrics, Mathematics - Statistics Theory |
| الوصف: | Debiased machine learning is a meta algorithm based on bias correction and sample splitting to calculate confidence intervals for functionals, i.e. scalar summaries, of machine learning algorithms. For example, an analyst may desire the confidence interval for a treatment effect estimated with a neural network. We provide a nonasymptotic debiased machine learning theorem that encompasses any global or local functional of any machine learning algorithm that satisfies a few simple, interpretable conditions. Formally, we prove consistency, Gaussian approximation, and semiparametric efficiency by finite sample arguments. The rate of convergence is $n^{-1/2}$ for global functionals, and it degrades gracefully for local functionals. Our results culminate in a simple set of conditions that an analyst can use to translate modern learning theory rates into traditional statistical inference. The conditions reveal a general double robustness property for ill posed inverse problems. Comment: Biometrika 2022 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2105.15197 |
| رقم الأكسشن: | edsarx.2105.15197 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |