Deep Surrogate

Deep surrogate models are artificial neural networks trained to approximate the behavior of computationally expensive simulations or complex systems, aiming to accelerate predictions and reduce computational costs. Current research focuses on improving surrogate accuracy and efficiency through techniques like incorporating nonlinearities, employing advanced architectures such as Graph Neural Networks and transformers, and optimizing training processes with active learning and multi-fidelity approaches. These advancements are significantly impacting diverse fields, from accelerating scientific simulations (e.g., fluid dynamics, PDE solvers) to optimizing resource allocation in edge computing and enhancing automated design processes (e.g., game AI).

Papers

May 20, 2024

Improving the Explain-Any-Concept by Introducing Nonlinearity to the Trainable Surrogate Model
Mounes Zaval, Sedat Ozer
Supervised ImageNet Explainable AI Segment Anything Model XAI Method Nonlinear Model Deep Surrogate XAI Based

April 25, 2024

In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization
Herilalaina Rakotoarison, Steven Adriaensen, Neeratyoy Mallik, Samir Garibov, Edward Bergman, Frank Hutter
Bayesian Optimization Hyperparameter Optimization Deep Surrogate Latent Space Bayesian Optimization

October 25, 2023

Learning Efficient Surrogate Dynamic Models with Graph Spline Networks
Chuanbo Hua, Federico Berto, Michael Poli, Stefano Massaroli, Jinkyoo Park
Deep Learning Ocean Current Deep Surrogate Spline Approximation Surrogate Dynamic

September 28, 2023

High Throughput Training of Deep Surrogates from Large Ensemble Runs
Lucas Meyer, Marc Schouler, Robert Alexander Caulk, Alejandro Ribés, Bruno Raffin
Deep Learning Numerical Solver Reservoir Dynamic Training Throughput Deep Surrogate Simulation Fidelity Simulation Ensemble

September 21, 2023

Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs
Alex Renda, Yi Ding, Michael Carbin
Training Data Sample Complexity Past Present Temporal Program Data Sampling Deep Surrogate Program Analysis Surrogate Study Assembling

June 28, 2023

Training Deep Surrogate Models with Large Scale Online Learning
Lucas Meyer, Marc Schouler, Robert Alexander Caulk, Alejandro Ribés, Bruno Raffin
Surrogate Model Deep Learning Algorithm Numerical Simulation PDE Solver Large Scale Learning Deep Surrogate

May 7, 2023

Disentangled Multi-Fidelity Deep Bayesian Active Learning
Dongxia Wu, Ruijia Niu, Matteo Chinazzi, Yian Ma, Rose Yu
Active Learning Multi Fidelity Deep Active Learning Deep Surrogate Low Precision Representation Multi Fidelity Active Learning

January 17, 2023

Multi-fidelity surrogate modeling for temperature field prediction using deep convolution neural network
Yunyang Zhang, Zhiqiang Gong, Weien Zhou, Xiaoyu Zhao, Xiaohu Zheng, Wen Yao
Neural Network Surrogate Modeling Multi Fidelity Temperature Field Deep Surrogate

December 2, 2022

DeepFT: Fault-Tolerant Edge Computing using a Self-Supervised Deep Surrogate Model
Shreshth Tuli, Giuliano Casale, Ludmila Cherkasova, Nicholas R. Jennings
Edge Computing Deep Surrogate Fault Prediction Edge Computing Paradigm

October 6, 2022

Data-driven Approaches to Surrogate Machine Learning Model Development
H. Rhys Jones, Tingting Mu, Andrei C. Popescu, Yusuf Sulehman
Machine Learning Loss Function Data Driven Approach Deep Surrogate Machine Learning Surrogate

August 4, 2022

Deep Surrogate of Modular Multi Pump using Active Learning
Malathi Murugesan, Kanika Goyal, Laure Barriere, Maura Pasquotti, Giacomo Veneri, Giovanni De Magistris
Active Learning Active Learning Framework Estimation Method Deep Surrogate

July 18, 2022

Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations
Hashmat Shadab Malik, Shahina K Kunhimon, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan
Additive Perturbation Transferable Adversarial Attack Adversarial Objective Pretext Task Deep Surrogate Restoration Network

July 11, 2022

Neural and spectral operator surrogates: unified construction and expression rate bounds
Lukas Herrmann, Christoph Schwab, Jakob Zech
Neural Topic Construction Industry Approximation Rate Deep Surrogate Operator Surrogate Rate Bound Polynomial Chaos

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

December 16, 2021

December 7, 2021

Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding
Yulun Zhang, Matthew C. Fontaine, Amy K. Hoover, Stefanos Nikolaidis
Diverse Datasets Play Style Quality Diversity Algorithm Deep Surrogate