Imagen de Portada

Formulations and scalability of neural network surrogates in nonlinear optimization problems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Parker, Robert B., Dowson, Oscar, LoGiudice, Nicole, Garcia, Manuel, Bent, Russell
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Transient Stability-Constrained OPF: Neural Network Surrogate Models and Pricing Stability
por: Garcia, Manuel, et al.
Publicado: (2025)

Nonlinear Optimization with GPU-Accelerated Neural Network Constraints
por: Parker, Robert, et al.
Publicado: (2025)

MathOptAI.jl: Embed trained machine learning predictors into JuMP models
por: Dowson, Oscar, et al.
Publicado: (2025)

Variable aggregation for nonlinear optimization problems
por: Naik, Sakshi, et al.
Publicado: (2025)

An analysis of optimization problems involving ReLU neural networks
por: Plate, Christoph, et al.
Publicado: (2025)

Exploiting block triangular submatrices in KKT systems
por: Parker, Robert, et al.
Publicado: (2026)

MultiObjectiveAlgorithms.jl: a Julia package for solving multi-objective optimization problems
por: Dowson, Oscar, et al.
Publicado: (2025)

Task-optimal data-driven surrogate models for eNMPC via differentiable simulation and optimization
por: Mayfrank, Daniel, et al.
Publicado: (2024)

Solving a class of stochastic optimal control problems by physics-informed neural networks
por: Jiao, Zhe, et al.
Publicado: (2024)

A General and Streamlined Differentiable Optimization Framework
por: Rosemberg, Andrew W., et al.
Publicado: (2025)

MathOptInterface: a data structure for mathematical optimization problems
por: Legat, Benoit, et al.
Publicado: (2020)

A constrained optimization approach to improve robustness of neural networks
por: Zhao, Shudian, et al.
Publicado: (2024)

Sobolev Training of End-to-End Optimization Proxies
por: Rosemberg, Andrew W., et al.
Publicado: (2025)

Efficient model predictive control for nonlinear systems modelled by deep neural networks
por: Lan, Jianglin
Publicado: (2024)

Time-optimal neural feedback control of nilpotent systems as a binary classification problem
por: Bicego, Sara, et al.
Publicado: (2025)

MIQCQP reformulation of the ReLU neural networks Lipschitz constant estimation problem
por: Sbihi, Mohammed, et al.
Publicado: (2024)

Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems
por: Dereich, Steffen, et al.
Publicado: (2025)

PolyFormer: learning efficient reformulations for scalable optimization under complex physical constraints
por: Wen, Yilin, et al.
Publicado: (2026)

MDP modeling for multi-stage stochastic programs
por: Morton, David P., et al.
Publicado: (2025)

Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks
por: Jentzen, Arnulf, et al.
Publicado: (2024)

Smart energy management: process structure-based hybrid neural networks for optimal scheduling and economic predictive control in integrated systems
por: Wu, Long, et al.
Publicado: (2024)

Graph neural networks for the prediction of molecular structure-property relationships
por: Rittig, Jan G., et al.
Publicado: (2022)

ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining
por: Sharman, Bharat, et al.
Publicado: (2025)

Global optimization of graph acquisition functions for neural architecture search
por: Xie, Yilin, et al.
Publicado: (2025)

Convergence of gradient flow for learning convolutional neural networks
por: Diederen, Jona-Maria, et al.
Publicado: (2026)

Size and depth of monotone neural networks: interpolation and approximation
por: Mikulincer, Dan, et al.
Publicado: (2022)

Quadratic models for understanding catapult dynamics of neural networks
por: Zhu, Libin, et al.
Publicado: (2022)

Residual subspace evolution strategies for nonlinear inverse problems
por: Alemanno, Francesco
Publicado: (2025)

A minimax optimal control approach for robust neural ODEs
por: Cipriani, Cristina, et al.
Publicado: (2023)

Reliably-stabilizing piecewise-affine neural network controllers
por: Fabiani, Filippo, et al.
Publicado: (2021)

Learning to accelerate distributed ADMM using graph neural networks
por: Doerks, Henri, et al.
Publicado: (2025)

Approximation and interpolation of deep neural networks
por: Constantinescu, Vlad-Raul, et al.
Publicado: (2023)

Mean-field neural networks-based algorithms for McKean-Vlasov control problems *
por: Pham, Huyên, et al.
Publicado: (2022)

Flowsheet synthesis through hierarchical reinforcement learning and graph neural networks
por: Stops, Laura, et al.
Publicado: (2022)

The duality structure gradient descent algorithm: analysis and applications to neural networks
por: Flynn, Thomas
Publicado: (2017)

A neural network-based approach to hybrid systems identification for control
por: Fabiani, Filippo, et al.
Publicado: (2024)

Tuning the burn-in phase in training recurrent neural networks improves their performance
por: Schiller, Julian D., et al.
Publicado: (2026)

On characterizing optimal learning trajectories in a class of learning problems
por: Befekadu, Getachew K
Publicado: (2025)

Verifying message-passing neural networks via topology-based bounds tightening
por: Hojny, Christopher, et al.
Publicado: (2024)

Convergence of continuous-time stochastic gradient descent with applications to deep neural networks
por: Lugosi, Gabor, et al.
Publicado: (2024)