Deep Inverse Optimization

Abstract

Given a set of observations generated by an optimization process, the goal of inverse optimization is to determine likely parameters of that process. We cast inverse optimization as a form of deep learning. Our method, called deep inverse optimization, is to unroll an iterative optimization process and then use backpropagation to learn parameters that generate the observations. We demonstrate that by backpropagating through the interior point algorithm we can learn the coefficients determining the cost vector and the constraints, independently or jointly, for both non-parametric and parametric linear programs, starting from one or multiple observations. With this approach, inverse optimization can leverage concepts and algorithms from deep learning.

References in corpus (6)

• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Gradient-based Hyperparameter Optimization through Reversible Learning
• Task-based End-to-end Model Learning in Stochastic Optimization
• Exponentially vanishing sub-optimal local minima in multilayer neural networks
• Learning Equations for Extrapolation and Control
• Generalized Inverse Optimization through Online Learning