Approximation theory of tree tensor networks: tensorized univariate functions

DOI10.1007/s00365-023-09620-warXiv2007.00118MaRDI QIDQ6076973

Anthony Nouy, Mazen Ali

Publication date: 17 October 2023

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.00118

zbMATH Keywords

neural networksBesov spacesapproximation spacestensor networksmatrix product statestensor trainsdirect (Jackson) and inverse (Bernstein) inequalities

Mathematics Subject Classification ID

Nontrigonometric harmonic analysis involving wavelets and other special systems (42C40) Learning and adaptive systems in artificial intelligence (68T05) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Approximation by polynomials (41A10) Spline approximation (41A15) Numerical approximation and computational geometry (primarily algorithms) (65D99)

Related Items (2)

Low-rank tensor methods for partial differential equations ⋮ Active Learning of Tree Tensor Networks using Optimal Least Squares

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A practical introduction to tensor networks: Matrix product states and projected entangled pair states
• The Hackbusch conjecture on tensor formats
• Tensor networks and hierarchical tensors for the solution of high-dimensional partial differential equations
• \(O(d \log N)\)-quantics approximation of \(N\)-\(d\) tensors in high-dimensional numerical modeling
• Adaptive near-optimal rank tensor approximation for high-dimensional operator equations
• Approximation of matrices with logarithmic number of parameters
• Quantized tensor-structured finite elements for second-order elliptic PDEs in two dimensions
• On the Dirac-Frenkel variational principle on tensor Banach spaces
• Higher-order principal component analysis for the approximation of tensors in tree-based low-rank formats
• Optimal nonlinear approximation
• Theory and practice of finite elements.
• On minimal subspaces in tensor representations
• Constructive representation of functions in low-rank tensor formats
• Tree-based tensor formats
• Approximation spaces of deep neural networks
• Exponential ReLU DNN expression of holomorphic maps in high dimension
• Learning with tree tensor networks: complexity estimates and model selection
• A new scheme for the tensor representation
• Error bounds for approximations with deep ReLU networks
• The Hackbusch conjecture on tensor formats. II.
• On manifolds of tensors of fixed TT-rank
• Approximation rates for the hierarchical tensor format in periodic Sobolev spaces
• Analysis of tensor approximation schemes for continuous functions
• Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 1 Low-Rank Tensor Decompositions
• Hierarchical Singular Value Decomposition of Tensors
• Tensor Spaces and Numerical Tensor Calculus
• Breaking the Curse of Dimensionality, Or How to Use SVD in Many Dimensions
• Interpolation of Besov Spaces
• Tensor-based multiscale method for diffusion problems in quasi-periodic heterogeneous media
• Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 2 Applications and Future Perspectives
• Solving the quantum many-body problem with artificial neural networks
• Approximation of Smoothness Classes by Deep Rectifier Networks
• LEARNING HIGH-DIMENSIONAL PROBABILITY DISTRIBUTIONS USING TREE TENSOR NETWORKS
• Deep ReLU networks and high-order finite element methods
• Causal structure of the entanglement renormalization ansatz
• An area law for one-dimensional quantum systems
• Real Analysis
• Geometry of tree-based tensor formats in tensor Banach spaces

This page was built for publication: Approximation theory of tree tensor networks: tensorized univariate functions