Dimension-independent learning rates for high-dimensional classification problems
From MaRDI portal
Cites work
- A deep network construction that adapts to intrinsic dimensionality beyond the domain
- Adaptive approximation and generalization of deep neural network with intrinsic dimensionality
- Approximation of infinitely differentiable multivariate functions is intractable
- Breaking the curse of dimensionality with convex neural networks
- Compactly supported shearlets are optimally sparse
- Deep learning
- Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
- Improved upper bounds for approximation by zonotopes
- Measure and integration theory. Transl. from the German by Robert B. Burckel
- Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks
- New tight frames of curvelets and optimal representations of objects with piecewise C2 singularities
- On the Theory of Dynamic Programming
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Optimally Sparse Multidimensional Representation Using Shearlets
- Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
- Provable approximation properties for deep neural networks
- Rates of approximation by ReLU shallow neural networks
- Solving high-dimensional partial differential equations using deep learning
- Universal approximation bounds for superpositions of a sigmoidal function
- What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory
This page was built for publication: Dimension-independent learning rates for high-dimensional classification problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7300003)
