Partial differential equation regularization for supervised machine learning
From MaRDI portal
Publication:4998637
Variational methods applied to PDEs (35A15) Smoothness and regularity of solutions to PDEs (35B65) Probabilistic models, generic numerical methods in probability and statistics (65C20) Numerical methods for partial differential equations, boundary value problems (65N99) Computational learning theory (68Q32) Artificial neural networks and deep learning (68T07)
Abstract: This article is an overview of supervised machine learning problems for regression and classification. Topics include: kernel methods, training by stochastic gradient descent, deep learning architecture, losses for classification, statistical learning theory, and dimension independent generalization bounds. Implicit regularization in deep learning examples are presented, including data augmentation, adversarial training, and additive noise. These methods are reframed as explicit gradient regularization.
Recommendations
- Machine learning for semi linear PDEs
- Learning partial differential equations via data discovery and sparse optimization
- Learning regularization functionals a supervised training approach
- scientific article; zbMATH DE number 7604708
- Solving partial differential equation based on extreme learning machine
- Deep learning methods for partial differential equations and related parameter identification problems
- Kernels, regularization and differential equations
- Regularization: From Inverse Problems to Large-Scale Machine Learning
- Using \(\ell _1\) regularization to improve numerical partial differential equation solvers
- Solving high-dimensional partial differential equations using deep learning
Cites work
- 10.1162/15324430260185628
- 10.1162/153244302760200704
- A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
- Deep learning
- Foundations of machine learning
- Geometric partial differential equations and image analysis
- scientific article; zbMATH DE number 6378127 (Why is no real title available?)
- scientific article; zbMATH DE number 45848 (Why is no real title available?)
- scientific article; zbMATH DE number 3551792 (Why is no real title available?)
- scientific article; zbMATH DE number 1249730 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Introductory lectures on convex optimization. A basic course.
- Matrix completion with the trace norm: learning, bounding, and transducing
- Nonlinear total variation based noise removal algorithms
- Optimization methods for large-scale machine learning
- Pattern recognition and machine learning.
- Robustness and generalization
- Statistical behavior and consistency of classification methods based on convex risk minimization.
Cited in
(6)- Deep limits of residual neural networks
- Generalization Error Analysis of Neural Networks with Gradient Based Regularization
- The kernel regularized learning algorithm for solving Laplace equation with Dirichlet boundary
- Implicit regularization with strongly convex bias: Stability and acceleration
- Topological Regularization via Persistence-Sensitive Optimization
- From kernel methods to neural networks: a unifying variational formulation
This page was built for publication: Partial differential equation regularization for supervised machine learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4998637)
