Strong mixed-integer programming formulations for trained neural networks.

*(English)*Zbl 1436.90088
Lodi, Andrea (ed.) et al., Integer programming and combinatorial optimization. 20th international conference, IPCO 2019, Ann Arbor, MI, USA, May 22–24, 2019. Proceedings. Cham: Springer. Lect. Notes Comput. Sci. 11480, 27-42 (2019).

Summary: We present an ideal mixed-integer programming (MIP) formulation for a rectified linear unit (ReLU) appearing in a trained neural network. Our formulation requires a single binary variable and no additional continuous variables beyond the input and output variables of the ReLU. We contrast it with an ideal “extended” formulation with a linear number of additional continuous variables, derived through standard techniques. An apparent drawback of our formulation is that it requires an exponential number of inequality constraints, but we provide a routine to separate the inequalities in linear time. We also prove that these exponentially-many constraints are facet-defining under mild conditions. Finally, we study network verification problems and observe that dynamically separating from the exponential inequalities (1) is much more computationally efficient and scalable than the extended formulation, (2) decreases the solve time of a state-of-the-art MIP solver by a factor of 7 on smaller instances, and (3) nearly matches the dual bounds of a state-of-the-art MIP solver on harder instances, after just a few rounds of separation and in orders of magnitude less time.

For the entire collection see [Zbl 1418.90011].

For the entire collection see [Zbl 1418.90011].