Provable approximation properties for deep neural networks
From MaRDI portal
Abstract: We discuss approximation of functions using deep neural nets. Given a function on a -dimensional manifold , we construct a sparsely-connected depth-4 neural network and bound its error in approximating . The size of the network depends on dimension and curvature of the manifold , the complexity of , in terms of its wavelet description, and only weakly on the ambient dimension . Essentially, our network computes wavelet functions, which are computed from Rectified Linear Units (ReLU)
Recommendations
- A note on the expressive power of deep rectified linear unit networks in high-dimensional spaces
- Error bounds for approximations with deep ReLU networks
- Deep network approximation characterized by number of neurons
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Approximation spaces of deep neural networks
Cites work
- An introduction to manifolds
- Approximation and learning by greedy algorithms
- Approximation by superpositions of a sigmoidal function
- Comparison of worst case errors in linear and neural network approximation
- Harmonic analysis on spaces of homogeneous type. With a preface by Yves Meyer
- Networks and the best approximation property
- On the tractability of multivariate integration and approximation by neural networks
- Sphere packings, lattices and groups. With additional contributions by E. Bannai, R. E. Borcherds, J. Leech, S. P. Norton, A. M. Odlyzko, R. A. Parker, L. Queen and B. B. Venkov.
- Universal approximation bounds for superpositions of a sigmoidal function
Cited in
(only showing first 100 items - show all)- Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs
- Topological properties of the set of functions generated by neural networks of fixed size
- Numerical solution of the parametric diffusion equation by deep neural networks
- Gabor neural networks with proven approximation properties
- Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem
- Approximation rates for neural networks with encodable weights in smoothness spaces
- Theory of deep convolutional neural networks. II: Spherical analysis
- A direct approach for function approximation on data defined manifolds
- High-dimensional distribution generation through deep neural networks
- Holomorphic feedforward networks
- The construction and approximation of ReLU neural network operators
- On the approximation of rough functions with deep neural networks
- Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples
- A measure theoretical approach to the mean-field maximum principle for training NeurODEs
- Representation formulas and pointwise properties for Barron functions
- A theoretical analysis of deep neural networks and parametric PDEs
- Nonlinear approximation and (deep) ReLU networks
- Depth separations in neural networks: what is actually being separated?
- Approximation spaces of deep neural networks
- Robust and resource-efficient identification of two hidden layer neural networks
- Universal approximation of symmetric and anti-symmetric functions
- Approximation properties of deep ReLU CNNs
- Theory of deep convolutional neural networks: downsampling
- Universal approximation with quadratic deep networks
- Rapid estimation of permeability from digital rock using 3D convolutional neural network
- PDE-Net 2.0: learning PDEs from data with a numeric-symbolic hybrid deep network
- Error bounds for approximations with deep ReLU networks
- Universality of deep convolutional neural networks
- MgNet: a unified framework of multigrid and convolutional neural network
- Analysis of time-frequency scattering transforms
- Machine learning based data retrieval for inverse scattering problems with incomplete data
- Side effects of learning from low-dimensional data embedded in a Euclidean space
- Growing axons: greedy learning of neural networks with application to function approximation
- Approximation with one-bit polynomials in Bernstein form
- On the proof complexity of deep inference
- Construct Deep Neural Networks based on Direct Sampling Methods for Solving Electrical Impedance Tomography
- Banach space representer theorems for neural networks and ridge splines
- The gap between theory and practice in function approximation with deep neural networks
- Deep Neural Network Approximation Theory
- Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models
- Approximation of smoothness classes by deep rectifier networks
- Optimal approximation with sparsely connected deep neural networks
- On PDE characterization of smooth hierarchical functions computed by neural networks
- Analysis of the generalization error: empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
- scientific article; zbMATH DE number 7626714 (Why is no real title available?)
- Approximations with deep neural networks in Sobolev time-space
- Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
- Surgery of frames in Hilbert spaces
- Full error analysis for the training of deep neural networks
- A note on the applications of one primary function in deep neural networks
- Wavelet neural networks functional approximation and application
- Any target function exists in a neighborhood of any sufficiently wide random network: a geometrical perspective
- Deep ReLU networks and high-order finite element methods
- Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
- Product formalisms for measures on spaces with binary tree structures: representation, visualization, and multiscale noise
- Adaptive approximation and generalization of deep neural network with intrinsic dimensionality
- Approximation properties of ridge functions and extreme learning machines
- Deep network approximation characterized by number of neurons
- Butterfly-net: optimal function representation based on convolutional neural networks
- Multi-scale deep neural network (MscaleDNN) for solving Poisson-Boltzmann equation in complex domains
- Equivalence of approximation by convolutional neural networks and fully-connected networks
- A note on the expressive power of deep rectified linear unit networks in high-dimensional spaces
- Deep hedging
- Deep neural networks for rotation-invariance approximation and learning
- Breaking the curse of dimensionality with convex neural networks
- Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
- A New Function Space from Barron Class and Application to Neural Network Approximation
- Neural network approximation
- A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations
- A deep network construction that adapts to intrinsic dimensionality beyond the domain
- Theory of deep convolutional neural networks. III: Approximating radial functions
- On the capacity of deep generative networks for approximating distributions
- Neural network approximation of continuous functions in high dimensions with applications to inverse problems
- Rates of approximation by ReLU shallow neural networks
- Deep learning methods for partial differential equations and related parameter identification problems
- On decision regions of narrow deep neural networks
- Deep ReLU neural networks in high-dimensional approximation
- Approximation Analysis of Convolutional Neural Networks
- Approximation of Lipschitz Functions Using Deep Spline Neural Networks
- Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation
- Limitations of neural network training due to numerical instability of backpropagation
- Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on Hölder Class
- Deep nonparametric estimation of intrinsic data structures by chart autoencoders: generalization error and robustness
- Neural network approximation and estimation of classifiers with classification boundary in a Barron class
- Approximation of nonlinear functionals using deep ReLU networks
- Quadratic Neural Networks for Solving Inverse Problems
- Designing universal causal deep learning models: The geometric (Hyper)transformer
- Error assessment of an adaptive finite elements -- neural networks method for an elliptic parametric PDE
- Provable Training of a ReLU Gate with an Iterative Non-Gradient Algorithm
- Approximation in shift-invariant spaces with deep ReLU neural networks
- Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations
- Tractability of approximation by general shallow networks
- Approximation of classifiers by deep perceptron networks
- Approximation of smooth functionals using deep ReLU networks
- Low dimensional approximation and generalization of multivariate functions on smooth manifolds using deep ReLU neural networks
- Approximation of functions from Korobov spaces by shallow neural networks
- Deep neural network expressivity for optimal stopping problems
- Computing ground states of Bose-Einstein condensation by normalized deep neural network
- Approximation results for gradient flow trained shallow neural networks in \(1d\)
- Deep Regression for Repeated Measurements
This page was built for publication: Provable approximation properties for deep neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1742817)
