Cover Image

Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Adams, Steven, Patanè, Andrea, Lahijanian, Morteza, Laurenti, Luca
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Error Bounds For Gaussian Process Regression Under Bounded Support Noise With Applications To Safety Certification
by: Reed, Robert, et al.
Published: (2024)

Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs
by: Kong, Chun-Wei, et al.
Published: (2024)

Uncertainty Propagation in Stochastic Systems via Mixture Models with Error Quantification
by: Figueiredo, Eduardo, et al.
Published: (2024)

Efficient Distribution Learning with Error Bounds in Wasserstein Distance
by: Figueiredo, Eduardo, et al.
Published: (2026)

Verification of Unknown Dynamical Systems via Autoencoder Latent Space
by: Reed, Robert, et al.
Published: (2025)

discretize_distributions: Efficient Quantization of Gaussian Mixtures with Guarantees in Wasserstein Distance
by: Adams, Steven, et al.
Published: (2025)

Promises of Deep Kernel Learning for Control Synthesis
by: Reed, Robert, et al.
Published: (2023)

A Unifying Perspective for Safety of Stochastic Systems: From Barrier Functions to Finite Abstractions
by: Laurenti, Luca, et al.
Published: (2023)

On the Robustness of Bayesian Neural Networks to Adversarial Attacks
by: Bortolussi, Luca, et al.
Published: (2022)

Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling
by: Sandberg, Jack, et al.
Published: (2025)

Learning Markov Processes as Sum-of-Square Forms for Analytical Belief Propagation
by: Amorese, Peter, et al.
Published: (2026)

Formal Verification of Unknown Dynamical Systems via Gaussian Process Regression
by: Skovbekk, John, et al.
Published: (2021)

Data-Driven Permissible Safe Control with Barrier Certificates
by: Mazouz, Rayan, et al.
Published: (2024)

Provably Safe Motion Planning Under Unknown Disturbances
by: Gracia, Ibon, et al.
Published: (2026)

Learning-Based Shielding for Safe Autonomy under Unknown Dynamics
by: Reed, Robert, et al.
Published: (2024)

Universal Learning of Stochastic Dynamics for Exact Belief Propagation using Bernstein Normalizing Flows
by: Amorese, Peter, et al.
Published: (2025)

IntervalMDP.jl: Accelerated Value Iteration for Interval Markov Decision Processes
by: Mathiesen, Frederik Baymler, et al.
Published: (2024)

Hybrid Energy-Based Models for Physical AI: Provably Stable Identification of Port-Hamiltonian Dynamics
by: Betteti, Simone, et al.
Published: (2026)

Shielded Deep Reinforcement Learning for Complex Spacecraft Tasking
by: Reed, Robert, et al.
Published: (2024)

Flow-Induced Diagonal Gaussian Processes
by: Lin, Moule, et al.
Published: (2025)

Provably Bounding Neural Network Preimages
by: Kotha, Suhas, et al.
Published: (2023)

Piecewise Control Barrier Functions for Stochastic Systems
by: Mazouz, Rayan, et al.
Published: (2025)

Stochastic Barrier Certificates in the Presence of Dynamic Obstacles
by: Mazouz, Rayan, et al.
Published: (2026)

Time-Varying Reach-Avoid Control Certificates for Stochastic Systems
by: Mazouz, Rayan, et al.
Published: (2026)

Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions
by: Mazouz, Rayan, et al.
Published: (2022)

Interval Markov Decision Processes with Continuous Action-Spaces
by: Delimpaltadakis, Giannis, et al.
Published: (2022)

Provable Bounds on the Hessian of Neural Networks: Derivative-Preserving Reachability Analysis
by: Sharifi, Sina, et al.
Published: (2024)

Stochastic Weight Sharing for Bayesian Neural Networks
by: Lin, Moule, et al.
Published: (2025)

Finite-Time Error Bounds for Greedy-GQ
by: Wang, Yue, et al.
Published: (2022)

Structured Diffusion Models with Mixture of Gaussians as Prior Distribution
by: Jia, Nanshan, et al.
Published: (2024)

Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control
by: Lederer, Armin, et al.
Published: (2019)

Provable Generalization Bounds for Deep Neural Networks with Momentum-Adaptive Gradient Dropout
by: Safder, Adeel
Published: (2025)

Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
by: Vertovec, Nikolaus, et al.
Published: (2025)

Theoretical Error Analysis of Entropy Approximation for Gaussian Mixtures
by: Furuya, Takashi, et al.
Published: (2022)

GGMPs: Generalized Gaussian Mixture Processes
by: Tekriwal, Vardaan, et al.
Published: (2026)

Data-Driven Strategy Synthesis for Stochastic Systems with Unknown Nonlinear Disturbances
by: Gracia, Ibon, et al.
Published: (2024)

Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
by: Boetius, David, et al.
Published: (2026)

Adaptive Soft Error Protection for Neural Network Processing
by: Xue, Xinghua, et al.
Published: (2024)

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees
by: Marzari, Luca, et al.
Published: (2023)

Provably Efficient Bayesian Optimization with Unknown Gaussian Process Hyperparameter Estimation
by: Ha, Huong, et al.
Published: (2023)