Model Reduction

Model reduction aims to create simplified, lower-dimensional representations of complex systems, improving computational efficiency without sacrificing significant accuracy. Current research emphasizes data-driven approaches, employing techniques like autoencoders, Koopman theory, and neural networks (including recurrent and convolutional architectures) to learn reduced-order models from high-fidelity data. These advancements are impacting diverse fields, enabling real-time control of systems like soft robots and accelerating simulations of turbulent flows and partial differential equations, ultimately enhancing scientific understanding and technological applications.

Papers

September 11, 2023

Data-Driven Model Reduction and Nonlinear Model Predictive Control of an Air Separation Unit by Applied Koopman Theory
Jan C. Schulze, Danimir T. Doncevic, Nils Erwes, Alexander Mitsos
Predictive Control Koopman Operator Separation Performance Nonlinear Model Predictive Control Model Reduction Koopman Model Data Driven Model Reduction

August 31, 2023

Training Neural Networks Using Reproducing Kernel Space Interpolation and Model Reduction
Eric Arthur Werneburg
Neural Network Kernel Hilbert Space Model Reduction Hilbert Space Kernel Interpolation Kernel Space

August 4, 2023

On stable wrapper-based parameter selection method for efficient ANN-based data-driven modeling of turbulent flows
Hyeongeun Yun, Yongcheol Choi, Youngjae Kim, Seongwon Kang
Model Reduction Turbulent Flow Parameter Selection Parameter Reduction

July 19, 2023

June 10, 2023

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
Haoran You, Huihong Shi, Yipin Guo, Yingyan, Lin
Vision Transformer Mixture Component Model Reduction Efficient Vision Transformer Simple Primitive Transformer Based Vision Shift Invariant Kernel

April 26, 2023

Tensor Decomposition for Model Reduction in Neural Networks: A Review
Xingyi Liu, Keshab K. Parhi
Neural Network Convolutional Neural Network Narrative Review Tensor Decomposition Model Reduction Tensor Decomposition Method Tensor Approximation

April 13, 2023

Canonical and Noncanonical Hamiltonian Operator Inference
Anthony Gruber, Irina Tezaur
Model Reduction Hamiltonian Learning Hamiltonian System

March 24, 2023

Achieving Occam's Razor: Deep Learning for Optimal Model Reduction
Botond B Antal, Anthony G Chesebro, Helmut H Strey, Lilianne R Mujica-Parodi, Corey Weistuch
Deep Learning Deep Neural Network Model Reduction Model Parameter Occam Algorithm

February 24, 2023

A DeepONet multi-fidelity approach for residual learning in reduced order modeling
Nicola Demo, Marco Tezzele, Gianluigi Rozza
Model Reduction Proper Orthogonal Decomposition Residual Learning Order Model

February 3, 2023

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
Yunchang Yang, Han Zhong, Tianhao Wu, Bin Liu, Liwei Wang, Simon S. Du
Sequential Decision Single Agent Sequential Decision Making Model Reduction Delayed Feedback Multi Agent Sequential Decision

January 31, 2023

Neural Control of Parametric Solutions for High-dimensional Evolution PDEs
Nathan Gaby, Xiaojing Ye, Haomin Zhou
Reduced Order Neural Network Controller Model Reduction High Dimensional Partial Differential Equation Parabolic Partial Differential Equation Parametric Solution

January 24, 2023

A two stages Deep Learning Architecture for Model Reduction of Parametric Time-Dependent Problems
Isabella Carla Gonnella, Martin W. Hess, Giovanni Stabile, Gianluigi Rozza
Time Varying Nonlinear Model Model Reduction Two Stage Deep Learning

January 20, 2023

Reinforcement learning-based estimation for partial differential equations
Saviz Mowlavi, Mouhacine Benosman
Reinforcement Learning Learning Based Partial Differential Equation Positive Reinforcement Control Policy Model Reduction Dimensional State Space Data Driven Reduced Order

January 17, 2023

Safety Verification of Neural Network Control Systems Using Guaranteed Neural Network Model Reduction
Weiming Xiang, Zhongzhu Shao
Neural Network Neural Network Controller Model Reduction Adaptive Cruise Control Safety Verification

November 30, 2022

November 28, 2022

Learning Coherent Clusters in Weakly-Connected Network Systems
Hancheng Min, Enrique Mallada
Graph Network Model Reduction Stochastic Block Model Large Scale Dynamic Connected Network Network Reduction

November 21, 2022

Modelling spatiotemporal turbulent dynamics with the convolutional autoencoder echo state network
Alberto Racca, Nguyen Anh Khoa Doan, Luca Magri
Reduced Order Echo State Network Model Reduction Turbulent Flow Global Attractor Spatiotemporal Fluid Process

November 19, 2022

Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Zhenglun Kong, Haoyu Ma, Geng Yuan, Mengshu Sun, Yanyue Xie, Peiyan Dong, Xin Meng, Xuan Shen, Hao Tang, Minghai Qin, Tianlong Chen, Xiaolong Ma, Xiaohui Xie, Zhangyang Wang, Yanzhi Wang
Vision Transformer End to End Sparse View Information Redundancy Model Reduction Training Datasets

Model Reduction

Papers

Data-Driven Model Reduction and Nonlinear Model Predictive Control of an Air Separation Unit by Applied Koopman Theory

Training Neural Networks Using Reproducing Kernel Space Interpolation and Model Reduction

On stable wrapper-based parameter selection method for efficient ANN-based data-driven modeling of turbulent flows

Practical Model Reductions for Verification of Multi-Agent Systems

Reinforcing POD-based model reduction techniques in reaction-diffusion complex networks using stochastic filtering and pattern recognition

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer

Tensor Decomposition for Model Reduction in Neural Networks: A Review

Canonical and Noncanonical Hamiltonian Operator Inference

Achieving Occam's Razor: Deep Learning for Optimal Model Reduction

A DeepONet multi-fidelity approach for residual learning in reduced order modeling

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

Neural Control of Parametric Solutions for High-dimensional Evolution PDEs

A two stages Deep Learning Architecture for Model Reduction of Parametric Time-Dependent Problems

Reinforcement learning-based estimation for partial differential equations

Safety Verification of Neural Network Control Systems Using Guaranteed Neural Network Model Reduction

Continuous Methods : Adaptively intrusive reduced order model closure

Task-Driven Hybrid Model Reduction for Dexterous Manipulation

Learning Coherent Clusters in Weakly-Connected Network Systems

Modelling spatiotemporal turbulent dynamics with the convolutional autoencoder echo state network

Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training