arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.08887cs.LGmath.OCstat.ML
收藏

一种智能预测-优化方法的风险界及其校正

Risk Bounds and Calibration for a Smart Predict-then-Optimize Method

University of California, Berkeley(加州大学伯克利分校)

Heyuan Liu, Paul Grigas

摘要:

预测-优化框架是实际随机决策问题的基础:首先预测优化模型的未知参数,然后使用预测值求解问题。该设置中的自然损失函数通过测量预测参数引起的决策误差来定义,Elmachtoub和Grigas将其命名为智能预测然后优化(SPO)损失[arXiv:1710.08005]。由于SPO损失通常是非凸的,并且可能是不连续的,因此Elmachtoub和Grigas [arXiv:1710.08005]引入了一个凸的替代项,称为SPO+损失,它重要地解释了优化模型的基础结构。在本文中,我们大大扩展了Elmachtoub和Grigas [arXiv:1710.08005]提供的SPO+损失的一致性结果。我们开发的SPO+损失相对于SPO损失的风险界限和统一的校准结果,这提供了一个定量的方法来转移超额替代风险超额真实风险。通过结合我们的风险界与推广界,我们表明,SPO+损失的经验最小化实现低超额真风险的概率很高。我们首先证明了这些结果的情况下,当潜在的优化问题的可行域是一个多面体,然后我们表明,结果可以大大加强时,可行域是一个强凸函数的水平集。我们进行实验,以经验证明SPO+替代品在投资组合分配和成本敏感型多类分类问题上与标准$\ell_1$和平方$\ell_2$预测误差损失相比的强度。

英文摘要:

The predict-then-optimize framework is fundamental in practical stochastic decision-making problems: first predict unknown parameters of an optimization model, then solve the problem using the predicted values. A natural loss function in this setting is defined by measuring the decision error induced by the predicted parameters, which was named the Smart Predict-then-Optimize (SPO) loss by Elmachtoub and Grigas [arXiv:1710.08005]. Since the SPO loss is typically nonconvex and possibly discontinuous, Elmachtoub and Grigas [arXiv:1710.08005] introduced a convex surrogate, called the SPO+ loss, that importantly accounts for the underlying structure of the optimization model. In this paper, we greatly expand upon the consistency results for the SPO+ loss provided by Elmachtoub and Grigas [arXiv:1710.08005]. We develop risk bounds and uniform calibration results for the SPO+ loss relative to the SPO loss, which provide a quantitative way to transfer the excess surrogate risk to excess true risk. By combining our risk bounds with generalization bounds, we show that the empirical minimizer of the SPO+ loss achieves low excess true risk with high probability. We first demonstrate these results in the case when the feasible region of the underlying optimization problem is a polyhedron, and then we show that the results can be strengthened substantially when the feasible region is a level set of a strongly convex function. We perform experiments to empirically demonstrate the strength of the SPO+ surrogate, as compared to standard $\ell_1$ and squared $\ell_2$ prediction error losses, on portfolio allocation and cost-sensitive multi-class classification problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑