Buchumschlag

Verifying message-passing neural networks via topology-based bounds tightening

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Hojny, Christopher, Zhang, Shiqiang, Campos, Juan S., Misener, Ruth
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Optimization and Control Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

Beyond adjacency: Graph encoding with reachability and shortest paths
von: Zhang, Shiqiang, et al.
Veröffentlicht: (2025)

P-split formulations: A class of intermediate formulations between big-M and convex hull for disjunctive constraints
von: Kronqvist, Jan, et al.
Veröffentlicht: (2022)

BARK: A Fully Bayesian Tree Kernel for Black-box Optimization
von: Boyne, Toby, et al.
Veröffentlicht: (2025)

Detecting and Handling Reflection Symmetries in Mixed-Integer (Nonlinear) Programming
von: Hojny, Christopher
Veröffentlicht: (2024)

BoGrape: Bayesian optimization over graphs with shortest-path encoded
von: Xie, Yilin, et al.
Veröffentlicht: (2025)

Robust stabilization of polytopic systems via fast and reliable neural network-based approximations
von: Fabiani, Filippo, et al.
Veröffentlicht: (2022)

On bounds for norms of reparameterized ReLU artificial neural network parameters: sums of fractional powers of the Lipschitz norm control the network parameter vector
von: Jentzen, Arnulf, et al.
Veröffentlicht: (2022)

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

Improved Physics-informed neural networks loss function regularization with a variance-based term
von: Hanna, John M., et al.
Veröffentlicht: (2024)

Global Optimization of Gaussian Process Acquisition Functions Using a Piecewise-Linear Kernel Approximation
von: Xie, Yilin, et al.
Veröffentlicht: (2024)

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

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

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

Meta-learning for sample-efficient Bayesian optimisation of fed-batch processes
von: Langdon, Becky, et al.
Veröffentlicht: (2026)

A computational comparison of handling distance constraints in MINLP
von: Hojny, Christopher, et al.
Veröffentlicht: (2026)

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

Formulations and scalability of neural network surrogates in nonlinear optimization problems
von: Parker, Robert B., et al.
Veröffentlicht: (2024)

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

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

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

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

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

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

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

Linear regression with overparameterized linear neural networks: Tight upper and lower bounds for implicit $\ell^1$-regularization
von: Matt, Hannes, et al.
Veröffentlicht: (2025)

Verifying Closed-Loop Contractivity of Learning-Based Controllers via Partitioning
von: Davydov, Alexander
Veröffentlicht: (2025)

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

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

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

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

Approximate non-linear model predictive control with safety-augmented neural networks
von: Hose, Henrik, et al.
Veröffentlicht: (2023)

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

Path-conditioned training: a principled way to rescale ReLU neural networks
von: Lebeurrier, Arthur, et al.
Veröffentlicht: (2026)

Branch-and-bound for integer D-Optimality with fast local search and variable-bound tightening
von: Ponte, Gabriel, et al.
Veröffentlicht: (2023)

Tightening convex relaxations of trained neural networks: a unified approach for convex and S-shaped activations
von: Carrasco, Pablo, et al.
Veröffentlicht: (2024)

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime
von: Barboni, Raphaël, et al.
Veröffentlicht: (2025)

Convergence of stochastic gradient descent under a local Lojasiewicz condition for deep neural networks
von: An, Jing, et al.
Veröffentlicht: (2023)

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

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