← 研踪 PaperTrailarXiv:2306.10081 · v5
Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization
首次提交 2023-06-16 15:07
版本更新 2026-11-17 05:03
雷达观测 2026-11-18 19:44
摘要
In data-driven optimization, the sample performance of the obtained decision typically incurs an optimistic bias against the true performance, a phenomenon commonly known as the Optimizer's Curse and intimately related to overfitting in machine learning. We develop a general approach that we call \emph{Optimizer's Information Criterion (OIC)} to correct this bias. OIC generalizes the celebrated Akaike Information Criterion from the evaluation of model adequacy, used primarily for model selection, to objective performance in data-driven optimization, which is used for decision selection. Our approach analytically approximates and cancels out the bias that comprises the interplay between model fitting and downstream optimization. As such, it saves the computational need to repeatedly solve optimization problems in cross-validation, while operating more generally than other bias approximating scheme. We apply OIC to a range of data-driven optimization formulations comprising empirical and parametric models, their regularized counterparts, and furthermore contextual optimization. Finally, we provide numerical validation of the superior performance of our approach under synthetic and real-world datasets.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v5 · 2026-11-17 05:03 · 最新观测版本
Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization
In data-driven optimization, the sample performance of the obtained decision typically incurs an optimistic bias against the true performance, a phenomenon commonly known as the Optimizer's Curse and intimately related to overfitting in machine learning. We develop a general approach that we call \emph{Optimizer's Information Criterion (OIC)} to correct this bias. OIC generalizes the celebrated Akaike Information Criterion from the evaluation of model adequacy, used primarily for model selection, to objective performance in data-driven optimization, which is used for decision selection. Our approach analytically approximates and cancels out the bias that comprises the interplay between model fitting and downstream optimization. As such, it saves the computational need to repeatedly solve optimization problems in cross-validation, while operating more generally than other bias approximating scheme. We apply OIC to a range of data-driven optimization formulations comprising empirical and parametric models, their regularized counterparts, and furthermore contextual optimization. Finally, we provide numerical validation of the superior performance of our approach under synthetic and real-world datasets.
查看此版本解读 →查看此版本原文 ↗