Neural network training using _1-regularization and bi-fidelity data

DOI10.1016/J.JCP.2022.111010OpenAlexW4213216104MaRDI QIDQ2138992FDOQ2138992

Authors: Subhayan De, Alireza Doostan 

Publication date: 17 May 2022

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.13011

Recommendations

• On robust training of regression neural networks
• Combining neural networks for function approximation under conditions of sparse data: the biased regression approach
• Improving neural network training solutions using regularisation
• Regularisation of neural networks by enforcing Lipschitz continuity
• Training neural networks with noisy data as an ill-posed problem
• Regularized greedy algorithms for network training with data noise

zbMATH Keywords

transfer learningneural networksuncertainty propagationscientific machine learningweighted \(\ell_1\)-regularization

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Numerical methods for partial differential equations, boundary value problems (65Nxx) Probabilistic methods, stochastic differential equations (65Cxx)

Cites Work

• Automated solution of differential equations by the finite element method. The FEniCS book
• The Adaptive Lasso and Its Oracle Properties
• Title not available (Why is that?)
• Reducing the Dimensionality of Data with Neural Networks
• Gaussian processes for machine learning.
• Enhancing sparsity by reweighted \(\ell _{1}\) minimization
• Deep learning
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Understanding machine learning. From theory to algorithms
• Compressed sensing
• A Stochastic Collocation Method for Elliptic Partial Differential Equations with Random Input Data
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• A survey of projection-based model reduction methods for parametric dynamical systems
• A Sparse Grid Stochastic Collocation Method for Partial Differential Equations with Random Input Data
• Multi-fidelity optimization via surrogate modelling
• A non-adapted sparse approximation of PDEs with stochastic inputs
• A stochastic projection method for fluid flow. II: Random process
• Accurate solutions to the square thermally driven cavity at high Rayleigh number
• A weighted \(\ell_1\)-minimization approach for sparse polynomial chaos expansions
• Uncertainty analysis for the steady-state flows in a dual throat nozzle
• Advanced Lectures on Machine Learning
• Practical error bounds for a non-intrusive bi-fidelity approach to parametric/stochastic model reduction
• Hidden physics models: machine learning of nonlinear partial differential equations
• Error bounds for approximations with deep ReLU networks
• Title not available (Why is that?)
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• A composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problems
• Bi-fidelity stochastic gradient descent for structural optimization under uncertainty
• Prediction of aerodynamic flow fields using convolutional neural networks
• The gap between theory and practice in function approximation with deep neural networks
• A MULTI-FIDELITY NEURAL NETWORK SURROGATE SAMPLING METHOD FOR UNCERTAINTY QUANTIFICATION
• ON TRANSFER LEARNING OF NEURAL NETWORKS USING BI-FIDELITY DATA FOR UNCERTAINTY PROPAGATION
• Data-driven prediction of unsteady flow over a circular cylinder using deep learning

Cited In (7)

• On sparse regression, \(L_p\)-regularization, and automated model discovery
• Multifidelity deep operator networks for data-driven and physics-informed problems
• A Neighborhood-Based Enhancement of the Gauss-Newton Bayesian Regularization Training Method
• Bi-fidelity modeling of uncertain and partially unknown systems using DeepONets
• Bi-fidelity variational auto-encoder for uncertainty quantification
• Combining neural networks for function approximation under conditions of sparse data: the biased regression approach
• A multifidelity machine learning based semi-Lagrangian finite volume scheme for linear transport equations and the nonlinear Vlasov-Poisson system

Uses Software

• FEniCS
• darch
• Adam

This page was built for publication: Neural network training using \(\ell_1\)-regularization and bi-fidelity data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2138992)