Machine learning from a continuous viewpoint. I
From MaRDI portal
Publication:829085
DOI10.1007/s11425-020-1773-8zbMath1472.68136arXiv1912.12777OpenAlexW3101985406MaRDI QIDQ829085
Publication date: 5 May 2021
Published in: Science China. Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1912.12777
Learning and adaptive systems in artificial intelligence (68T05) Variational problems in a geometric measure-theoretic setting (49Q20) Numerical methods of relaxation type (49M20)
Related Items
The Continuous Formulation of Shallow Neural Networks as Wasserstein-Type Gradient Flows, SPINN: sparse, physics-based, and partially interpretable neural networks for PDEs, Revealing hidden dynamics from time-series data by ODENet, On the Exact Computation of Linear Frequency Principle Dynamics and Its Generalization, Stochastic asymptotical regularization for linear inverse problems, A Riemannian mean field formulation for two-layer neural networks with batch normalization, A rigorous framework for the mean field limit of multilayer neural networks, High order spatial discretization for variational time implicit schemes: Wasserstein gradient flows and reaction-diffusion systems, A mathematical perspective of machine learning, Unnamed Item, A blob method for inhomogeneous diffusion with applications to multi-agent control and sampling, Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs, Learning domain-independent Green's function for elliptic partial differential equations, Unnamed Item, Machine Learning and Computational Mathematics, Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks, A Multi-Scale DNN Algorithm for Nonlinear Elliptic Equations with Multiple Scales, The Random Feature Model for Input-Output Maps between Banach Spaces, Generalization error of GAN from the discriminator's perspective, Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning, Representation formulas and pointwise properties for Barron functions
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Nonlinear total variation based noise removal algorithms
- \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Harmonic analysis of neural networks
- The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
- DGM: a deep learning algorithm for solving partial differential equations
- A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
- Solving many-electron Schrödinger equation using deep neural networks
- A priori estimates of the population risk for two-layer neural networks
- Mean field analysis of neural networks: a central limit theorem
- Solving for high-dimensional committor functions using artificial neural networks
- A mean-field optimal control formulation of deep learning
- Neural network with unbounded activation functions is universal approximator
- A proposal on machine learning via dynamical systems
- Optimal approximations by piecewise smooth functions and associated variational problems
- The theory of optimal processes. I. The maximum principle
- Universal approximation bounds for superpositions of a sigmoidal function
- The Variational Formulation of the Fokker--Planck Equation
- Stable architectures for deep neural networks
- Solving the quantum many-body problem with artificial neural networks
- Ridgelets: a key to higher-dimensional intermittency?
- 10.1162/153244303321897690
- A mean field view of the landscape of two-layer neural networks
- Solving high-dimensional partial differential equations using deep learning
- Reconciling modern machine-learning practice and the classical bias–variance trade-off
- Machine Learning: Mathematical Theory and Scientific Applications
- Breaking the Curse of Dimensionality with Convex Neural Networks
- Understanding Machine Learning
- Theory and Applications of Smoothed Particle Hydrodynamics
- Optimal Transport
- Approximation by superpositions of a sigmoidal function
