Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data
From MaRDI portal
Publication:5857926
DOI10.1137/20M1326404zbMath1468.65220arXiv2102.07169OpenAlexW3132786502MaRDI QIDQ5857926
Lexing Ying, Zhihan Li, Yu-Wei Fan
Publication date: 8 April 2021
Published in: Multiscale Modeling & Simulation (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2102.07169
Ridge regression; shrinkage estimators (Lasso) (62J07) Multigrid methods; domain decomposition for boundary value problems involving PDEs (65N55) Probabilistic models, generic numerical methods in probability and statistics (65C20) Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05) Neural nets and related approaches to inference from stochastic processes (62M45)
Related Items
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- The heterogeneous multiscale methods
- Kernel methods in machine learning
- Fast algorithm for extracting the diagonal of the inverse matrix with application to the electronic structure analysis of metallic systems
- The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
- Products of many large random matrices and gradients in deep neural networks
- Just interpolate: kernel ``ridgeless regression can generalize
- BCR-net: A neural network based on the nonstandard wavelet form
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Solving electrical impedance tomography with deep learning
- MgNet: a unified framework of multigrid and convolutional neural network
- Solving for high-dimensional committor functions using artificial neural networks
- A multiscale neural network based on hierarchical nested bases
- Band-Edge Solitons, Nonlinear Schrödinger/Gross–Pitaevskii Equations, and Effective Media
- Multilevel Monte Carlo Path Simulation
- Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
- Survey of Multifidelity Methods in Uncertainty Propagation, Inference, and Optimization
- Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling
- Computing the Ground State Solution of Bose--Einstein Condensates by a Normalized Gradient Flow
- Solving parametric PDE problems with artificial neural networks
- A multi-level procedure for enhancing accuracy of machine learning algorithms
- A Multiscale Neural Network Based on Hierarchical Matrices
- Solving inverse problems using data-driven models
- SwitchNet: A Neural Network Model for Forward and Inverse Scattering Problems
- The Rademacher Complexity of Linear Transformation Classes
- Wide neural networks of any depth evolve as linear models under gradient descent *
