Strong Mixed-Integer Programming Formulations for Trained Neural Networks
Authors:
- Joey HuchetteJHJoey Huchette
- Juan Pablo VielmaJVJuan Pablo Vielma
- 13 April 2019
- book chapter
- Published by Springer Nature
- p. 27-42
Abstract
No abstract availableKeywords
All Related Versions
This publication has 29 references indexed in Scilit:
- A lagrangian propagator for artificial neural networks in constraint programmingConstraints, 2015
- Deep learningNature, 2015
- On mathematical programming with indicator constraintsMathematical Programming, 2015
- Mixed Integer Linear Programming Formulation TechniquesSIAM Review, 2015
- Mixed-integer nonlinear programs featuring “on/off” constraintsComputational Optimization and Applications, 2011
- Neuron Constraints to Model Complex Real-World Problems2011
- Modeling disjunctive constraints with a logarithmic number of binary variables and constraintsMathematical Programming, 2009
- Disjunctive programming: Properties of the convex hull of feasible pointsDiscrete Applied Mathematics, 1998
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Disjunctive Programming and a Hierarchy of Relaxations for Discrete Optimization ProblemsSIAM Journal on Algebraic Discrete Methods, 1985