Multi Fidelity Gaussian Process

Multi-fidelity Gaussian processes (MFGPs) are statistical models designed to efficiently leverage data from multiple sources with varying accuracy and computational cost, improving prediction accuracy and reducing reliance on expensive high-fidelity simulations. Current research focuses on extending MFGPs to handle more than two fidelity levels, incorporating heterogeneous input spaces, and applying them to diverse problems including differential equation discovery, biomanufacturing process modeling, and uncertainty quantification in high-dimensional systems. This approach offers significant advantages in fields where high-fidelity data is scarce or expensive to obtain, leading to improved model accuracy and efficiency in various scientific and engineering applications.

Papers

April 18, 2024

Multi-fidelity Gaussian process surrogate modeling for regression problems in physics
Kislaya Ravi, Vladyslav Fediukov, Felix Dietrich, Tobias Neckel, Fabian Buse, Michael Bergmann, Hans-Joachim Bungartz
Surrogate Modeling Theoretical Physic Multi Fidelity Regression Problem Multi Fidelity Gaussian Process Single Fidelity

March 19, 2024

Multi-fidelity surrogate with heterogeneous input spaces for modeling melt pools in laser-directed energy deposition
Nandana Menon, Amrita Basak
Multi Fidelity Thermal Simulation Heterogeneous Input Energy Deposition Melt Pool Multi Fidelity Gaussian Process

January 22, 2024

Sparse discovery of differential equations based on multi-fidelity Gaussian process
Yuhuang Meng, Yue Qiu
Uncertainty Quantification Surrogate Model Differential Equation Gaussian Process Regression Sparse Identification Multi Fidelity Gaussian Process Sparse Model Discovery

November 26, 2022

Multi-fidelity Gaussian Process for Biomanufacturing Process Modeling with Small Data
Yuan Sun, Winton Nathan-Roberts, Tien Dung Pham, Ellen Otte, Uwe Aickelin
Gaussian Process Regression Small Datasets Multi Fidelity Gaussian Process

August 16, 2022

Rain Removal from Light Field Images with 4D Convolution and Multi-scale Gaussian Process
Tao Yan, Mingyue Li, Bin Li, Yang Yang, Rynson W. H. Lau
Light Field Rain Removal Rainy Image Multi Fidelity Gaussian Process 4 Dimensional Convolution

April 11, 2022

RMFGP: Rotated Multi-fidelity Gaussian process with Dimension Reduction for High-dimensional Uncertainty Quantification
Jiahao Zhang, Shiqi Zhang, Guang Lin
Gaussian Process Dimension Reduction Multi Fidelity Multi Fidelity Gaussian Process High Dimensional Uncertainty

December 15, 2021

Fast characterization of inducible regions of atrial fibrillation models with multi-fidelity Gaussian process classification
Lia Gander, Simone Pezzuto, Ali Gharaviri, Rolf Krause, Paris Perdikaris, Francisco Sahli Costabal
Atrial Fibrillation Quantitative Characterization Ablation Study Annotation Region Multi Fidelity Gaussian Process

November 10, 2021

Safe Real-Time Optimization using Multi-Fidelity Gaussian Processes
Panagiotis Petsagkourakis, Benoit Chachuat, Ehecatl Antonio del Rio-Chanona
Gaussian Process Derivative Free Optimization Multi Fidelity Gaussian Process

Multi Fidelity Gaussian Process

Papers

Multi-fidelity Gaussian process surrogate modeling for regression problems in physics

Multi-fidelity surrogate with heterogeneous input spaces for modeling melt pools in laser-directed energy deposition

Sparse discovery of differential equations based on multi-fidelity Gaussian process

Multi-fidelity Gaussian Process for Biomanufacturing Process Modeling with Small Data

Rain Removal from Light Field Images with 4D Convolution and Multi-scale Gaussian Process

RMFGP: Rotated Multi-fidelity Gaussian process with Dimension Reduction for High-dimensional Uncertainty Quantification

Fast characterization of inducible regions of atrial fibrillation models with multi-fidelity Gaussian process classification

Safe Real-Time Optimization using Multi-Fidelity Gaussian Processes