Strong mixed-integer programming formulations for trained neural networks
From MaRDI portal
Publication:5918909
DOI10.1007/s10107-020-01474-5zbMath1450.90014arXiv1811.01988OpenAlexW2901816197MaRDI QIDQ5918909
No author found.
Publication date: 28 August 2020
Published in: Mathematical Programming. Series A. Series B, Integer Programming and Combinatorial Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1811.01988
Related Items (21)
Ideal, non-extended formulations for disjunctive constraints admitting a network representation ⋮ Unnamed Item ⋮ JANOS: An Integrated Predictive and Prescriptive Modeling Framework ⋮ Modeling design and control problems involving neural network surrogates ⋮ The role of optimization in some recent advances in data-driven decision-making ⋮ Principled deep neural network training through linear programming ⋮ Getting away with more network pruning: from sparsity to geometry and linear regions ⋮ OAMIP: optimizing ANN architectures using mixed-integer programming ⋮ On data-driven chance constraint learning for mixed-integer optimization problems ⋮ Towards Lower Bounds on the Depth of ReLU Neural Networks ⋮ On mathematical optimization for clustering categories in contingency tables ⋮ Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networks ⋮ Optimization of sparsity-constrained neural networks as a mixed integer linear program ⋮ Deep Neural Networks Pruning via the Structured Perspective Regularization ⋮ BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic ⋮ Advances in verification of ReLU neural networks ⋮ Strong mixed-integer programming formulations for trained neural networks ⋮ Compact mixed-integer programming formulations in quadratic optimization ⋮ An outer-approximation guided optimization approach for constrained neural network inverse problems ⋮ A two-stage exact algorithm for optimization of neural network ensemble ⋮ Between steps: intermediate relaxations between big-M and convex hull formulations
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Mixed-integer nonlinear programs featuring ``on/off constraints
- Empirical decision model learning
- Modeling disjunctive constraints with a logarithmic number of binary variables and constraints
- Disjunctive programming: Properties of the convex hull of feasible points
- The Cayley trick, lifting subdivisions and the Bohne-Dress theorem on zonotopal tilings
- Deep neural networks and mixed integer linear optimization
- Strong formulations for quadratic optimization with M-matrices and indicator variables
- Deterministic global optimization with artificial neural networks embedded
- Convexification and global optimization in continuous and mixed-integer nonlinear programming. Theory, algorithms, software, and applications
- Reluplex: an efficient SMT solver for verifying deep neural networks
- Small and strong formulations for unions of convex sets from the Cayley embedding
- On mathematical programming with indicator constraints
- On handling indicator constraints in mixed integer programming
- A Lagrangian propagator for artificial neural networks in constraint programming
- Mixed Integer Linear Programming Formulation Techniques
- Persistency Model and Its Applications in Choice Modeling
- Modelling with integer variables
- Robustness against dependence in PERT: An application of duality and distributions with known marginals
- Disjunctive Programming and a Hierarchy of Relaxations for Discrete Optimization Problems
- Stochastic Bounds on Distributions of Optimal Value Functions with Applications to PERT, Network Flows and Reliability
- Combinatorial optimization. Theory and algorithms
- Strong mixed-integer programming formulations for trained neural networks
This page was built for publication: Strong mixed-integer programming formulations for trained neural networks
