Convex and concave envelopes of artificial neural network activation functions for deterministic global optimization
From MaRDI portal
Publication:2689856
DOI10.1007/s10898-022-01228-xOpenAlexW4293660124MaRDI QIDQ2689856
Matthew D. Stuber, Matthew E. Wilhelm, Chen-Yu Wang
Publication date: 14 March 2023
Published in: Journal of Global Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10898-022-01228-x
deterministic global optimizationartificial neural networksmachine learningenvelopesfactorable programmingMcCormick relaxationsJulia programming
Related Items
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Improved relaxations for the parametric solutions of ODEs using differential inequalities
- Differentiable McCormick relaxations
- Convergence analysis of multivariate McCormick relaxations
- Convergence rate of McCormick relaxations
- Generalized McCormick relaxations
- The cluster problem revisited
- Expected energy-based restricted Boltzmann machine for classification
- The cluster problem in multivariate global optimization
- A reduced space branch and bound algorithm for global optimization.
- Deep neural networks and mixed integer linear optimization
- A hybrid LP/NLP paradigm for global optimization relaxations
- The cluster problem in constrained global optimization
- Deterministic global optimization of process flowsheets in a reduced space using McCormick relaxations
- Corrections to: ``Differentiable McCormick relaxations
- Multilayer feedforward networks are universal approximators
- Deterministic global optimization with artificial neural networks embedded
- A polyhedral branch-and-cut approach to global optimization
- A branch-and-reduce approach to global optimization
- Deep neural networks motivated by partial differential equations
- Deterministic global optimization with Gaussian processes embedded
- Optimization-based convex relaxations for nonconvex parametric systems of ordinary differential equations
- Between steps: intermediate relaxations between big-M and convex hull formulations
- Obey validity limits of data-driven models through topological data analysis and one-class classification
- ANTIGONE: algorithms for coNTinuous/Integer global optimization of nonlinear equations
- A general framework for convexity analysis in deterministic global optimization
- Nonlinear convex and concave relaxations for the solutions of parametric ODEs
- Convex and concave relaxations of implicit functions
- Julia: A Fresh Approach to Numerical Computing
- McCormick-Based Relaxations of Algorithms
- Introduction to Interval Analysis
- LAPACK Users' Guide
- Computability of global solutions to factorable nonconvex programs: Part I — Convex underestimating problems
- Stable architectures for deep neural networks
- SCIP: global optimization of mixed-integer nonlinear programs in a branch-and-cut framework
- EAGO.jl: easy advanced global optimization in Julia
- Dying ReLU and Initialization: Theory and Numerical Examples
- Implicit Deep Learning
- An updated set of basic linear algebra subprograms (BLAS)
- Benchmarking optimization software with performance profiles.
