A multi-level procedure for enhancing accuracy of machine learning algorithms

DOI10.1017/S0956792520000224zbMath1482.65149arXiv1909.09448OpenAlexW2987480747MaRDI QIDQ5014840

Roberto Molinaro, Kjetil O. Lye, Siddhartha Mishra

Publication date: 8 December 2021

Published in: European Journal of Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1909.09448

zbMATH Keywords

variance reductionmachine learningmulti-level algorithmsuncertainity quantification

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Bayesian inference (62F15) Bayesian problems; characterization of Bayes procedures (62C10) Finite difference methods for initial value and initial-boundary value problems involving PDEs (65M06) Finite volume methods for initial value and initial-boundary value problems involving PDEs (65M08) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75)

Related Items (6)

A physics-informed multi-fidelity approach for the estimation of differential equations parameters in low-data or large-noise regimes ⋮ Multi-index ensemble Kalman filtering ⋮ Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences ⋮ Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data ⋮ Connections between deep learning and partial differential equations ⋮ Higher-Order Quasi-Monte Carlo Training of Deep Neural Networks

Uses Software

• Adam
• DeepONet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-level Monte Carlo finite volume methods for nonlinear systems of conservation laws in multi-dimensions
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Deep learning observables in computational fluid dynamics
• Hidden physics models: machine learning of nonlinear partial differential equations
• Multilayer feedforward networks are universal approximators
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Error bounds for approximations with deep ReLU networks
• A machine learning framework for data driven acceleration of computations of differential equations
• An artificial neural network as a troubled-cell indicator
• On the mathematical foundations of learning
• Sparse tensor multi-level Monte Carlo finite volume methods for hyperbolic conservation laws with random initial data
• Multilevel Monte Carlo Methods
• Multilevel Monte Carlo Path Simulation
• Survey of Multifidelity Methods in Uncertainty Propagation, Inference, and Optimization
• Statistical solutions of hyperbolic systems of conservation laws: Numerical approximation
• Solving high-dimensional partial differential equations using deep learning
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
• Entropy Stable Scheme on Two-Dimensional Unstructured Grids for Euler Equations
• Understanding Machine Learning
• Approximation by superpositions of a sigmoidal function

This page was built for publication: A multi-level procedure for enhancing accuracy of machine learning algorithms