Optimization over trained neural networks: going large with gradient-based algorithms
From MaRDI portal
Cites work
- Advances in verification of ReLU neural networks
- Approximation by superpositions of a sigmoidal function
- Benchmarking optimization software with performance profiles.
- Computability of global solutions to factorable nonconvex programs: Part I — Convex underestimating problems
- Constraint learning to define trust regions in optimization over pre-trained predictive models
- Deep neural networks and mixed integer linear optimization
- Deterministic global optimization with artificial neural networks embedded
- Error bounds for approximations with deep ReLU networks
- Global minimization via piecewise-linear underestimation
- Globally convergent algorithms for robust pole assignment by state feedback
- JANOS: An Integrated Predictive and Prescriptive Modeling Framework
- Mixed-integer models for nonseparable piecewise-linear optimization: unifying framework and extensions
- Multilayer feedforward networks are universal approximators
- Nonconvex Piecewise Linear Functions: Advanced Formulations and Simple Modeling Tools
- On mathematical programming with indicator constraints
- Optimization with constraint learning: a framework and survey
- Piecewise-linear approximations of multidimensional functions
- Some methods of speeding up the convergence of iteration methods
- Strong mixed-integer programming formulations for trained neural networks
- Structured pruning of neural networks for constraints learning
- The Gradient Projection Method for Nonlinear Programming. Part I. Linear Constraints
This page was built for publication: Optimization over trained neural networks: going large with gradient-based algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7356193)
