Conformal Predictive Programming for Chance Constrained Optimization
CoRR(2024)
摘要
Motivated by the advances in conformal prediction (CP), we propose conformal
predictive programming (CPP), an approach to solve chance constrained
optimization (CCO) problems, i.e., optimization problems with nonlinear
constraint functions affected by arbitrary random parameters. CPP utilizes
samples from these random parameters along with the quantile lemma – which is
central to CP – to transform the CCO problem into a deterministic optimization
problem. We then present two tractable reformulations of CPP by: (1) writing
the quantile as a linear program along with its KKT conditions (CPP-KKT), and
(2) using mixed integer programming (CPP-MIP). CPP comes with marginal
probabilistic feasibility guarantees for the CCO problem that are conceptually
different from existing approaches, e.g., the sample approximation and the
scenario approach. While we explore algorithmic similarities with the sample
approximation approach, we emphasize that the strength of CPP is that it can
easily be extended to incorporate different variants of CP. To illustrate this,
we present robust conformal predictive programming to deal with distribution
shifts in the uncertain parameters of the CCO problem.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要