Machine Learning-Augmented Optimization of Large Bilevel and Two-stage Stochastic Programs: Application to Cycling Network Design

arXiv:2209.09404v3 Announce Type: replace-cross
Abstract: Motivated by a cycling infrastructure planning application, we present a machine learning approach to solving bilevel programs with a large number of independent followers, which as a special case includes two-stage stochastic programming. We propose an optimization model that explicitly considers a sampled subset of followers and exploits a machine learning model to estimate the objective values of unsampled followers. Unlike existing approaches, we embed machine learning model training into the optimization problem, which allows …

abstract application arxiv case cs.lg cycling design independent infrastructure machine machine learning math.oc network optimization planning programming stage stochastic type