Surrogate Modeling Toolbox

A Python-based toolbox of various methods in decision making, uncertainty quantification and statistical emulation: multi-fidelity, experimental design, Bayesian optimisation, Bayesian quadrature, etc.

DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks

Distributed Asynchronous Hyperparameter Optimization better than HyperOpt. 比HyperOpt更强的分布式异步超参优化库。

Collection of Multi-Fidelity benchmark functions

[NeurIPS 2022] Supervising the Multi-Fidelity Race of Hyperparameter Configurations

A set of reactor design benchmark problems to evaluate high-dimensional, expensive, and potentially multi-fidelity optimisation algorithms.

This repository comprises Jupyter Notebooks that serve as supplementary material to the journal article titled "Review of Multifidelity Models." The notebooks contain Python-based implementations that demonstrate toy problems in the multifidelity domain.

Project source code and data for multi-fidelity machine learning strategy for flame model identification

Flexible Gaussian Process model with user friendly kernel and mean function construction inspired by STHENO.

A suite of codes for dynamic analysis of offshore slender structures

Just a notebook reproducing the Non-linear Autoregressive Gaussian Process (Perdikaris et al, 2017) using Tensorflow Probability

A Python-based toolbox of various methods in uncertainty quantification and statistical emulation: multi-fidelity, experimental design, Bayesian optimisation, Bayesian quadrature, etc.

[NeurIPS 2022] Supervising the Multi-Fidelity Race of Hyperparameter Configurations

Multi-fidelity modeling of wind farm wakes based on a novel super-fidelity network

This repository contains research on multi-fidelity Bayesian optimization, that I have presented on the Physics Days 2022

[NeurIPS 2023] Multi-fidelity hyperparameter optimization with deep power laws that achieves state-of-the-art results across diverse benchmarks.

Code for the paper "Multi-Fidelity Best-Arm Identification" (NeurIPS 2022)

Vanishing Viscosity solution predicting Graph Neural Networks and Domain Decomposable Reduced Order Models based on the Discontinuous Galerking method applied to Friedrichs' systems