Surrogate Model

Surrogate models are computationally efficient approximations of complex simulations, primarily used to accelerate optimization, uncertainty quantification, and design exploration in various scientific and engineering fields. Current research emphasizes developing accurate and robust surrogate models using diverse machine learning architectures, including neural networks (e.g., convolutional, recurrent, and graph convolutional networks), Gaussian processes, and normalizing flows, often incorporating techniques like Bayesian optimization and active learning to improve efficiency. The widespread adoption of surrogate models significantly reduces computational costs associated with high-fidelity simulations, enabling faster design iterations, more comprehensive uncertainty analyses, and ultimately, more efficient scientific discovery and technological advancement.

Papers

August 4, 2022

Reliability analysis of discrete-state performance functions via adaptive sequential sampling with detection of failure surfaces
Miroslav Vořechovský
Data Detection Surrogate Model Object Surface Rare Event Robust Method Reliability Analysis Failure Probability Performance Function

August 3, 2022

GAS: Generating Fast and Accurate Surrogate Models for Autonomous Vehicle Systems
Keyur Joshi, Chiao Hsieh, Sayan Mitra, Sasa Misailovic
Autonomous Driving Surrogate Model Autonomous Driving System Fuel Information

August 2, 2022

s-LIME: Reconciling Locality and Fidelity in Linear Explanations
Romaric Gaudel, Luis Galárraga, Julien Delaunay, Laurence Rozé, Vaishnavi Bhargava
Surrogate Model Black Box Model Fidelity Reward Structured Explanation Black Box Machine Learning Model Dseg Lime LIME Explanation

July 25, 2022

VDL-Surrogate: A View-Dependent Latent-based Model for Parameter Space Exploration of Ensemble Simulations
Neng Shi, Jiayi Xu, Haoyu Li, Hanqi Guo, Jonathan Woodring, Han-Wei Shen
Surrogate Model Parameter Space Exploration Simulation Ensemble Surrogate Model Training

July 23, 2022

Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers
Björn Lütjens, Catherine H. Crawford, Campbell D Watson, Christopher Hill, Dava Newman
Surrogate Model Surrogate Modeling Grid Based Scale Dynamic

July 18, 2022

Vertical GaN Diode BV Maximization through Rapid TCAD Simulation and ML-enabled Surrogate Model
Albert Lu, Jordan Marshall, Yifan Wang, Ming Xiao, Yuhao Zhang, Hiu Yung Wong
Surrogate Model Differential Evolution

July 11, 2022

Efficient Learning of Accurate Surrogates for Simulations of Complex Systems
A. Diaw, M. McKerns, I. Sagert, L. G. Stanton, M. S. Murillo
Simulation Study Surrogate Model Efficient Learning Complex System Sampling Based Optimization Response Surface Learnable Surrogate Token Nuclear Model

July 5, 2022

A Deep Learning Approach for the solution of Probability Density Evolution of Stochastic Systems
Seid H. Pourtakdoust, Amir H. Khodabakhsh
Surrogate Model Solution Path Deep Learning Approach Stochastic System Physic Constrained Density Evolution

June 24, 2022

Deep Active Learning for Regression Using $\epsilon$-weighted Hybrid Query Strategy
Harsh Vardhan, Janos Sztipanovits
Active Learning Surrogate Model Novel Regression Deep Active Learning Design Optimization High Dimensional Problem Hybrid Query

June 22, 2022

Dynamic Multi-objective Ensemble of Acquisition Functions in Batch Bayesian Optimization
Jixiang Chen, Fu Luo, Zhenkun Wang
Bayesian Optimization Surrogate Model Multi Objective Optimization Problem Acquisition Function Batch Bayesian Optimization Expensive Optimization

June 17, 2022

A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models
Andrew Bolt, Carolyn Huston, Petra Kuhnert, Joel Janek Dabrowski, James Hilton, Conrad Sanderson
Spatio Temporal Surrogate Model Spatio Temporal Prediction Basic Emulator

June 16, 2022

Boosting the Adversarial Transferability of Surrogate Models with Dark Knowledge
Dingcheng Yang, Zihao Xiao, Wenjian Yu
Adversarial Example Surrogate Model Hidden Knowledge Deep Surrogate

June 12, 2022

Machine learning based surrogate modeling with SVD enabled training for nonlinear civil structures subject to dynamic loading
Siddharth S. Parida, Supratik Bose, Megan Butcher, Georgios Apostolakis, Prashant Shekhar
Training Data Surrogate Model Surrogate Modeling Singular Value Decomposition Structural Dynamic Dynamic Loading Earthquake Engineering Ground Motion

June 9, 2022

Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination
Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Harald Oberhauser, Michael A. Osborne
Surrogate Model Bayesian Posterior Efficient Bayesian Inference Bayesian Quadrature Simultaneous Inference Kernel Quadrature

June 7, 2022

Recent Advances in Bayesian Optimization
Xilu Wang, Yaochu Jin, Sebastian Schmitt, Markus Olhofer
Bayesian Optimization Surrogate Model Recent Advance

June 6, 2022

Information-theoretic Inducing Point Placement for High-throughput Bayesian Optimisation
Henry B. Moss, Sebastian W. Ober, Victor Picheny
Surrogate Model Sparse Model Bayesian Optimisation Sparse Gaussian Process Surrogate Modelling

May 31, 2022

Towards Explainable Metaheuristic: Mining Surrogate Fitness Models for Importance of Variables
Manjinder Singh, Alexander E. I. Brownlee, David Cairns
Surrogate Model Genetic Algorithm Importance Aware Variable Model Fitness Approximation Interpretable Algorithm

May 28, 2022

Uncertainty quantification of two-phase flow in porous media via coupled-TgNN surrogate model
Jian Li, Dongxiao Zhang, Tianhao He, Qiang Zheng
Uncertainty Quantification Surrogate Model Multiphase Flow Data Driven Surrogate Porous Medium Subsurface Flow

May 27, 2022

Surrogate modeling for Bayesian optimization beyond a single Gaussian process
Qin Lu, Konstantinos D. Polyzos, Bingcong Li, Georgios B. Giannakis
Bayesian Optimization Surrogate Model Hyperparameter Tuning Surrogate Modeling Probabilistic Surrogate

May 24, 2022

Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning
Rocco Palmitessa, Morten Grum, Allan Peter Engsig-Karup, Roland Löwe
Surrogate Model Hydrological Model Hydrodynamic Simulation

Surrogate Model

Papers

Reliability analysis of discrete-state performance functions via adaptive sequential sampling with detection of failure surfaces

GAS: Generating Fast and Accurate Surrogate Models for Autonomous Vehicle Systems

s-LIME: Reconciling Locality and Fidelity in Linear Explanations

VDL-Surrogate: A View-Dependent Latent-based Model for Parameter Space Exploration of Ensemble Simulations

Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers

Vertical GaN Diode BV Maximization through Rapid TCAD Simulation and ML-enabled Surrogate Model

Efficient Learning of Accurate Surrogates for Simulations of Complex Systems

A Deep Learning Approach for the solution of Probability Density Evolution of Stochastic Systems

Deep Active Learning for Regression Using $\epsilon$-weighted Hybrid Query Strategy

Dynamic Multi-objective Ensemble of Acquisition Functions in Batch Bayesian Optimization

A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models

Boosting the Adversarial Transferability of Surrogate Models with Dark Knowledge

Machine learning based surrogate modeling with SVD enabled training for nonlinear civil structures subject to dynamic loading

Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination

Recent Advances in Bayesian Optimization

Information-theoretic Inducing Point Placement for High-throughput Bayesian Optimisation

Towards Explainable Metaheuristic: Mining Surrogate Fitness Models for Importance of Variables

Uncertainty quantification of two-phase flow in porous media via coupled-TgNN surrogate model

Surrogate modeling for Bayesian optimization beyond a single Gaussian process

Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning