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

December 8, 2023

Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models
Qiang Liu, Nils Thuerey
Surrogate Model Probabilistic Model Denoising Diffusion Probabilistic Model Turbulence Model Turbulence Simulation Uncertainty Aware Surrogate Model

December 7, 2023

November 21, 2023

November 19, 2023

Coverage-Validity-Aware Algorithmic Recourse
Ngoc Bui, Duy Nguyen, Man-Chung Yue, Viet Anh Nguyen
Surrogate Model Algorithmic Recourse Robust Recourse Stein Coverage

November 15, 2023

Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation
Vaishnavi Shrivastava, Percy Liang, Ananya Kumar
Large Language Model Question Answering Surrogate Model GPT Neo Confidence Estimation Whispering Llama Confidence Estimation Model

November 7, 2023

Operational risk quantification of power grids using graph neural network surrogates of the DC OPF
Yadong Zhang, Pranav M Karve, Sankaran Mahadevan
Graph Drawing Surrogate Model Power Grid Power System Neural Network Surrogate Operational Risk

October 23, 2023

Neural Network with Local Converging Input (NNLCI) for Supersonic Flow Problems with Unstructured Grids
Weiming Ding, Haoxiang Huang, Tzu Jung Lee, Yingjie Liu, Vigor Yang
Neural Network Surrogate Model Unstructured Grid Hypersonic Flow Shock Wave

October 18, 2023

Applications of ML-Based Surrogates in Bayesian Approaches to Inverse Problems
Pelin Ersin, Emma Hayes, Peter Matthews, Paramjyoti Mohapatra, Elisa Negrini, Karl Schulz
Financial Application Inverse Problem Surrogate Model Bayesian Approach Wave Equation Machine Learning Based Surrogate

October 17, 2023

Understanding Fairness Surrogate Functions in Algorithmic Fairness
Wei Yao, Zhanke Zhou, Zhicong Li, Bo Han, Yong Liu
Procedural Fairness Surrogate Model Algorithmic Fairness Surrogate Function Fairness Verification

October 16, 2023

October 12, 2023

Hyperparameter Adaptive Search for Surrogate Optimization: A Self-Adjusting Approach
Nazanin Nezami, Hadis Anahideh
Surrogate Model Hyperparameter Optimization Hyperparameter Tuning Self Adaptation Global Optimization Problem

October 4, 2023

September 25, 2023

Uncertainty Aware Deep Learning for Particle Accelerators
Kishansingh Rajput, Malachi Schram, Karthik Somayaji
Surrogate Model Uncertainty Aware Beam Prediction Particle Accelerator Uncertainty Aware Deep Learning

Surrogate Model

Papers

Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models

Enhancing Polynomial Chaos Expansion Based Surrogate Modeling using a Novel Probabilistic Transfer Learning Strategy

Surrogate Modelling for Sea Ice Concentration using Lightweight Neural Ensemble

Optimizing $CO_{2}$ Capture in Pressure Swing Adsorption Units: A Deep Neural Network Approach with Optimality Evaluation and Operating Maps for Decision-Making

Towards Sobolev Pruning

Constrained Bayesian Optimization Under Partial Observations: Balanced Improvements and Provable Convergence

Multi-fidelity Bayesian Optimization in Engineering Design

The limitation of neural nets for approximation and optimization

Coverage-Validity-Aware Algorithmic Recourse

Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation

Operational risk quantification of power grids using graph neural network surrogates of the DC OPF

Neural Network with Local Converging Input (NNLCI) for Supersonic Flow Problems with Unstructured Grids

Applications of ML-Based Surrogates in Bayesian Approaches to Inverse Problems

Understanding Fairness Surrogate Functions in Algorithmic Fairness

Accurate Data-Driven Surrogates of Dynamical Systems for Forward Propagation of Uncertainty

Combating Label Noise With A General Surrogate Model For Sample Selection

Hyperparameter Adaptive Search for Surrogate Optimization: A Self-Adjusting Approach

Progressive reduced order modeling: empowering data-driven modeling with selective knowledge transfer

Multiple Physics Pretraining for Physical Surrogate Models

Uncertainty Aware Deep Learning for Particle Accelerators