Classical Physics-informed neural networks (PINNs) approximate solutions to PDEs with the help of deep neural networks trained to satisfy the differential operator and the relevant boundary conditions. We revisit this idea in the quantum computing realm, using parameterised random quantum circuits as trial solutions. We further adapt recent PINN-based techniques to our quantum setting, in particular Gaussian smoothing. Our analysis concentrates on the Poisson, the Heat and the Hamilton-Jacobi-Bellman equations, which are ubiquitous in most areas of science. On the theoretical side, we develop a complexity analysis of this approach, and show numerically that random quantum networks can outperform more traditional quantum networks as well as random classical networks.
An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator
The University of Arizona(亚利桑那大学);Massachusetts Institute of Technology(麻省理工学院)
Neural Measures for learning distributions of Random PDEs
DMAM, University of Crete, Greece(DMAM,希腊克里特大学);IACM, Foundation for Research and Technology - Hellas, Greece(IACM,希腊基础研究与技术研究所);MPS, University of Sussex, United Kingdom(MPS,英国 Sussex 大学)
HEATNETs: Explainable Random Feature Neural Networks for High-Dimensional Parabolic PDEs
Modelling and Engineering Risk and Complexity, Scuola Superiore Meridionale(南方高等学院建模与工程风险与复杂性研究中心);Hopkins Extreme Materials Institute and Dept. of Chemical and Biomolecular Engineering, Johns Hopkins University(约翰斯·霍普金斯大学霍普金斯极端材料研究所和化学与生物分子工程系);Department of Statistics and Stochastic Modelling and Applications Laboratory, Athens University of Economics and Business(雅典经济与商业大学统计学与随机建模与应用实验室)
Partition of Unity Physics-Informed Neural Networks (POU-PINNs): An Unsupervised Framework for Physics-Informed Domain Decomposition and Mixtures of Experts
The University of Texas at El Paso(德克萨斯大学埃尔帕索分校);University of California, Santa Cruz(加州大学圣克鲁兹分校);Clarkson University(克拉克森大学);Texas A&M University in Kingsville(德克萨斯农工大学金斯维尔分校)
Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
Peking University(北京大学);Huawei Technologies Co. Ltd(华为技术有限公司);Beijing International Center for Mathematical Research, Peking University(北京国际数学研究中心(北京大学));Center for Machine Learning Research, Peking University(北京大学机器学习研究中心)
Stability and Bifurcation Analysis of Nonlinear PDEs via Random Projection-based PINNs: A Krylov-Arnoldi Approach
Hopkins Extreme Materials Institute, Johns Hopkins University(霍普金斯极端材料研究所,约翰霍普金斯大学);Dept. of Chemical and Biomolecular Engineering, Johns Hopkins University(化学与生物分子工程系,约翰霍普金斯大学);School of Chemical Engineering, National Technical University of Athens(希腊技术大学化学工程学院);Dipartimento di Matematica e Applicazioni “Renato Caccioppoli”, Università degli Studi di Napoli Federico II(那不勒斯费德里科二世大学Renato Caccioppoli数学与应用系);Dept. of Applied Mathematics and Statistics, Johns Hopkins University(应用数学与统计学系,约翰霍普金斯大学)
Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations
Department of Mathematical Sciences, KAIST(韩国科学技术院数学科学系);Department of Statistics and Data Science, Yonsei University(延世大学统计与数据科学系);Department of Applied Statistics, Yonsei University(延世大学应用统计学系);Department of Quantum Information, Yonsei University(延世大学量子信息系);Department of Mathematical Sciences, Seoul National University(首尔国立大学数学科学系)