Approximation of functions of few variables in high dimensions
Many high-dimensional computational problems depend in fact on much fewer variables than originally assumed. It is important for practical computations to reduce this high (say, \(N\)) dimensional problem to fewer variables (say, \(\ell\)), and this process is known as dimension reduction. The reason for this is the so-called curse of dimensionality which states that the higher the number of variables is, the more complicated (far more complicated, that is) becomes the problem. There are several approaches to solving this question, and one of the issues is the question whether we know which ones the smaller number of coordinates are or whether we do not know that. The former case is settled to some extend, in the sense that there are error estimates for the reduced problem as compared to the original problem which depend on the number of function values we have and on the \(Lip1\)-norm of the approximand. The latter alternative is addressed in this paper where a certain number of adaptively chosen function values have to be provided to get the same order of estimates as in the former case. This number is, of course, larger, typically by a \(O(\log N)\) factor (times a factor that depends on \(\ell\)). Algorithms are explicitly provided for the mentioned adaptive choice of function evaluations.
- Best subset selection, persistence in high-dimensional statistical learning and optimization under l₁ constraint
- Compressed sensing
- Compressed sensing and best \(k\)-term approximation
- Convergence rates for sparse chaos approximations of elliptic problems with stochastic coefficients
- Diffusion wavelets
- scientific article; zbMATH DE number 878862 (Why is no real title available?)
- Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
- Learning juntas
- New bounds for perfect hashing via information theory
- On the Size of Separating Systems and Families of Perfect Hash Functions
- Stable signal recovery from incomplete and inaccurate measurements
- Tractability of multivariate problems. Volume I: Linear information
- Optimal maximization and approximation algorithms for approximately calculated functions of many variables
- Uniform recovery of high-dimensional C^r-functions
- Learning general sparse additive models from point queries in high dimensions
- Sparse harmonic transforms: a new class of sublinear-time algorithms for learning functions of many variables
- Sparse harmonic transforms. II: Best \(s\)-term approximation guarantees for bounded orthonormal product bases in sublinear-time
- Sparse mixture models inspired by ANOVA decompositions
- Generalization bounds for sparse random feature expansions
- Information based complexity for high dimensional sparse functions
- Sampling schemes and recovery algorithms for functions of few coordinate variables
- Approximation of generalized ridge functions in high dimensions
- On some aspects of approximation of ridge functions
- Capturing ridge functions in high dimensions from point queries
- Complexity of approximation of functions of few variables in high dimensions
- \(N\)-widths and \(\varepsilon \)-dimensions for high-dimensional approximations
- On two continuum armed bandit problems in high dimensions
- Zeroth-order nonconvex stochastic optimization: handling constraints, high dimensionality, and saddle points
- Tensor products of approximation spaces associated with regular elliptic operators
- scientific article; zbMATH DE number 3857670 (Why is no real title available?)
- On ``freezing of unessential variables
- A survey of compressed sensing
- Learning functions of few arbitrary linear parameters in high dimensions
- scientific article; zbMATH DE number 852148 (Why is no real title available?)
- Interpretable approximation of high-dimensional data
- Grouped transformations and regularization in high-dimensional explainable ANOVA approximation
- Jointly low-rank and bisparse recovery: questions and partial answers
- Neural network approximation
- Fast hyperbolic wavelet regression meets ANOVA
- Approximation of curve-based sleeve functions in high dimensions
- On the approximability and curse of dimensionality of certain classes of high-dimensional functions
- Variable transformations in combination with wavelets and ANOVA for high-dimensional approximation
- ANOVA-boosting for random Fourier features
- Fast and interpretable support vector classification based on the truncated ANOVA decomposition
- Worst-Case Completion of Tensors with Approximately Few ANOVA Terms
- On n-widths of a Sobolev function class in Orlicz spaces
- Adaptive near-optimal rank tensor approximation for high-dimensional operator equations
This page was built for publication: Approximation of functions of few variables in high dimensions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q623354)
