Optimization Online


ReLU Networks as Surrogate Models in Mixed-Integer Linear Programs

Bjarne Grimstad (bjarne.grimstad***at***gmail.com)
Henrik Andersson (henrik.andersson***at***ntnu.no)

Abstract: We consider the embedding of piecewise-linear deep neural networks (ReLU networks) as surrogate models in mixed-integer linear programming (MILP) problems. A MILP formulation of ReLU networks has recently been applied by many authors to probe for various model properties subject to input bounds. The formulation is obtained by programming each ReLU operator with a binary variable and applying the big-M method. The efficiency of the formulation hinges on the tightness of the bounds defined by the big-M values. When ReLU networks are embedded in a larger optimization problem, the presence of output bounds can be exploited in bound tightening. To this end, we devise and study several bound tightening procedures that consider both input and output bounds. Our numerical results show that bound tightening may reduce solution times considerably, and that small-sized ReLU networks are suitable as surrogate models in mixed-integer linear programs.

Keywords: Deep Neural Networks; ReLU Networks; Mixed-Integer Linear Programming; Surrogate Modeling; Regression

Category 1: Integer Programming ((Mixed) Integer Linear Programming )


Download: [PDF]

Entry Submitted: 07/06/2019
Entry Accepted: 07/07/2019
Entry Last Modified: 07/07/2019

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society