تقرير
Regret Bounds and Experimental Design for Estimate-then-Optimize
| العنوان: | Regret Bounds and Experimental Design for Estimate-then-Optimize |
|---|---|
| المؤلفون: | Tan, Samuel, Frazier, Peter I. |
| سنة النشر: | 2022 |
| المجموعة: | Mathematics Statistics |
| مصطلحات موضوعية: | Mathematics - Optimization and Control, Statistics - Machine Learning |
| الوصف: | In practical applications, data is used to make decisions in two steps: estimation and optimization. First, a machine learning model estimates parameters for a structural model relating decisions to outcomes. Second, a decision is chosen to optimize the structural model's predicted outcome as if its parameters were correctly estimated. Due to its flexibility and simple implementation, this ``estimate-then-optimize'' approach is often used for data-driven decision-making. Errors in the estimation step can lead estimate-then-optimize to sub-optimal decisions that result in regret, i.e., a difference in value between the decision made and the best decision available with knowledge of the structural model's parameters. We provide a novel bound on this regret for smooth and unconstrained optimization problems. Using this bound, in settings where estimated parameters are linear transformations of sub-Gaussian random vectors, we provide a general procedure for experimental design to minimize the regret resulting from estimate-then-optimize. We demonstrate our approach on simple examples and a pandemic control application. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2210.15576 |
| رقم الأكسشن: | edsarx.2210.15576 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |