Deterministic global optimization with artificial neural networks embedded
From MaRDI portal
Abstract: Artificial neural networks (ANNs) are used in various applications for data-driven black-box modeling and subsequent optimization. Herein, we present an efficient method for deterministic global optimization of ANN embedded optimization problems. The proposed method is based on relaxations of algorithms using McCormick relaxations in a reduced-space [ extit{SIOPT}, 20 (2009), pp. 573-601] including the convex and concave envelopes of the nonlinear activation function of ANNs. The optimization problem is solved using our in-house global deterministic solver MAiNGO. The performance of the proposed method is shown in four optimization examples: an illustrative function, a fermentation process, a compressor plant and a chemical process optimization. The results show that computational solution time is favorable compared to the global general-purpose optimization solver BARON.
Recommendations
- Convex and concave envelopes of artificial neural network activation functions for deterministic global optimization
- scientific article; zbMATH DE number 1961132
- Advances in Neural Networks – ISNN 2005
- Generation of Optimal Artificial Neural Networks Using a Pattern Search Algorithm: Application to Approximation of Chemical Systems
- A hybrid artificial neural network method with uniform design for structural optimization
Cites work
- scientific article; zbMATH DE number 3649911 (Why is no real title available?)
- scientific article; zbMATH DE number 4055377 (Why is no real title available?)
- scientific article; zbMATH DE number 2121575 (Why is no real title available?)
- A polyhedral branch-and-cut approach to global optimization
- A reduced space branch and bound algorithm for global optimization.
- ANTIGONE: algorithms for coNTinuous/Integer global optimization of nonlinear equations
- CONOPT—A Large-Scale GRG Code
- Computability of global solutions to factorable nonconvex programs: Part I — Convex underestimating problems
- Convergence analysis of multivariate McCormick relaxations
- Convergence rate of McCormick relaxations
- Convex and concave relaxations of implicit functions
- Corrections to: ``Differentiable McCormick relaxations
- Deterministic global optimization of process flowsheets in a reduced space using McCormick relaxations
- Differentiable McCormick relaxations
- Erratum to: ``Multivariate McCormick relaxations
- FILIB++, a fast interval library supporting containment computations
- Generalized McCormick relaxations
- Global optimization. Theory, algorithms, and applications
- McCormick-Based Relaxations of Algorithms
- Multilayer feedforward networks are universal approximators
- Multivariate McCormick relaxations
- Reverse propagation of McCormick relaxations
- Three enhancements for optimization-based bound tightening
- Tighter McCormick relaxations through subgradient propagation
Cited in
(23)- JANOS: An Integrated Predictive and Prescriptive Modeling Framework
- DeCODe: a community-based algorithm for generating high-quality decompositions of optimization problems
- Revisiting `survival of the fittest' principle in global stochastic optimisation: incorporating anisotropic mutations
- Tighter McCormick relaxations through subgradient propagation
- A two-stage exact algorithm for optimization of neural network ensemble
- Comparison of MINLP formulations for global superstructure optimization
- Modeling design and control problems involving neural network surrogates
- Extended McCormick relaxation rules for handling empty arguments representing infeasibility
- Deterministic global optimization with Gaussian processes embedded
- Improved convex and concave relaxations of composite bilinear forms
- Obey validity limits of data-driven models through topological data analysis and one-class classification
- scientific article; zbMATH DE number 1961132 (Why is no real title available?)
- Surrogate-based branch-and-bound algorithms for simulation-based black-box optimization
- Mixed-Integer Convex Nonlinear Optimization with Gradient-Boosted Trees Embedded
- Advances in Neural Networks – ISNN 2005
- Globally optimal bounding ellipsoid algorithm for parameter estimation using artificial neural networks
- Globally optimal scheduling of an electrochemical process via data-driven dynamic modeling and wavelet-based adaptive grid refinement
- Working fluid selection for organic rankine cycles via deterministic global optimization of design and operation
- Data-driven spatial branch-and-bound algorithms for box-constrained simulation-based optimization
- Convex and concave envelopes of artificial neural network activation functions for deterministic global optimization
- Implementation of black box models for internal ballistics optimization using an artificial neural network
- Surrogate models of radiative transfer codes for atmospheric trace gas retrievals from satellite observations
- Generation of Optimal Artificial Neural Networks Using a Pattern Search Algorithm: Application to Approximation of Chemical Systems
Describes a project that uses
Uses Software
This page was built for publication: Deterministic global optimization with artificial neural networks embedded
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1730780)
