Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences

DOI10.1137/20M1344883MaRDI QIDQ5001377

T. Konstantin Rusch, Siddhartha Mishra

Publication date: 19 July 2021

Published in: SIAM Journal on Numerical Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2005.12564

zbMATH Keywords

low-discrepancy sequencesquasi-Monte Carlogeneralization errordeep learningdeep neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Algorithms for approximation of functions (65D15) Numerical quadrature and cubature formulas (65D32) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65M99)

Related Items

Compliance minimisation of smoothly varying multiscale structures using asymptotic analysis and machine learning ⋮ A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations ⋮ Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification ⋮ On the approximation of functions by tanh neural networks ⋮ Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms ⋮ Convergence Analysis of a Quasi-Monte CarloBased Deep Learning Algorithm for Solving Partial Differential Equations ⋮ wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws ⋮ Approximation bounds for convolutional neural networks in operator learning ⋮ Finite Neuron Method and Convergence Analysis ⋮ A physics-informed multi-fidelity approach for the estimation of differential equations parameters in low-data or large-noise regimes ⋮ Higher-Order Quasi-Monte Carlo Training of Deep Neural Networks

Uses Software

• redbKIT
• PyTorch
• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integrals
• Deep learning observables in computational fluid dynamics
• Hidden physics models: machine learning of nonlinear partial differential equations
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Efficient basket Monte Carlo option pricing via a simple analytical approximation
• A priori estimates of the population risk for two-layer neural 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
• Multilevel Higher Order QMC Petrov--Galerkin Discretization for Affine Parametric Operator Equations
• Handbook of Uncertainty Quantification
• Multilevel Monte Carlo Path Simulation
• Monte Carlo Variance of Scrambled Net Quadrature
• Solving high-dimensional partial differential equations using deep learning
• A multi-level procedure for enhancing accuracy of machine learning algorithms
• Multidimensional Variation for Quasi-Monte Carlo
• High-dimensional integration: The quasi-Monte Carlo way
• Advanced Lectures on Machine Learning
• Understanding Machine Learning
• Reduced Basis Methods for Partial Differential Equations
• On the distribution of points in a cube and the approximate evaluation of integrals
• Transformations and Hardy--Krause Variation