Gaussian averages of interpolated bodies and applications to approximate reconstruction
In this paper, results motivated by problems coming from convex-geometry and from non-parametric statistics (learning theory) are obtained. Let \(e_1,\dots,e_n\) be the standard basis in \(\mathbb{R}^n\) endowed with the canonical Euclidean structure, and let \(\{g_i\}_1^n\) be independent \(\mathcal{N}(0,1)\) Gaussian random variables. Let \(T\subset\mathbb{R}^n\), and consider the sets \(T_{\rho}=T\cap\rho B_2^n\), where \(B_2^n\) is the unit Euclidean ball. The purpose of the paper is to look for bounds of \(l_{\ast}(T_{\rho}):=E\sup_{l\in T_{\rho}}\langle\sum_{i=1}^ng_ie_i,t\rangle\) as a function of \(\rho\). Sharp bounds are established when \(T=B_p^n\) for \(1\leq p\leq\infty\) (namely, the unit ball of the \(l_p^n\)-norm, defined as \(\| x\| _p=\left(\sum_i| x_i| ^p\right)^{\frac{1}{p}}\) for \(p<\infty\), and \(\| x\| _{\infty}=\sup_i| x_i| \)), or \(T=B_{p\infty}^n\) for \(0<p\leq 1\) (namely the unit bal of the so-called weak \(l_p^n\)-norm). In fact, sharp bounds are also obtained when \(B_2^n\) is replaced by \(B_q^n\). An application to statistics is presented in connection with the so-called approximate reconstruction problem. Also, applications to convex geometry are discussed by showing that the control of \(l_{\ast}(T_{\rho})\) allows the control of the diameter of \(k\)-codimensional sections of \(T\) for an appropriate \(k\), so that the main results of the paper have immediate consequences for the diameter of sections. Precise estimates are provided in some cases.
- Reconstruction and subgaussian operators in asymptotic geometric analysis
- Gaussian convex bodies: a nonasymptotic approach
- Gaussian processes and almost spherical sections of convex bodies
- Diameters of sections and coverings of convex bodies
- A remark on the diameter of random sections of convex bodies
- A Note on an Observation of G. Schechtman
- Almost Euclidean Quotient Spaces of Subspaces of a Finite-Dimensional Normed Space
- Asymptotic formulas for the diameter of sections of symmetric convex bodies
- Atomic Decomposition by Basis Pursuit
- Decoding by Linear Programming
- Diameters of sections and coverings of convex bodies
- DIAMETERS OF SOME FINITE-DIMENSIONAL SETS AND CLASSES OF SMOOTH FUNCTIONS
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution
- Geometric approach to error-correcting codes and reconstruction of signals
- scientific article; zbMATH DE number 1574604 (Why is no real title available?)
- scientific article; zbMATH DE number 4157247 (Why is no real title available?)
- scientific article; zbMATH DE number 3944477 (Why is no real title available?)
- scientific article; zbMATH DE number 3944537 (Why is no real title available?)
- scientific article; zbMATH DE number 4061904 (Why is no real title available?)
- scientific article; zbMATH DE number 194093 (Why is no real title available?)
- Interpolation of Quasi-Normed Spaces.
- Isoperimetry of waists and local versus global asymptotic convex geometries
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- NORMS OF RANDOM MATRICES AND WIDTHS OF FINITE-DIMENSIONAL SETS
- On the minimum of several random variables
- Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ 1 minimization
- Orlicz norms of sequences of random variables
- Random Euclidean sections of some classical Banach spaces
- Stable recovery of sparse overcomplete representations in the presence of noise
- Subspaces of Small Codimension of Finite-Dimensional Banach Spaces
- Volumetric invariants and operators on random families of Banach spaces
- Estimating averages of order statistics of bivariate functions
- \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
- Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions
- Estimates for order statistics in terms of quantiles
- Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
- Phase retrieval: stability and recovery guarantees
- Reconstruction and subgaussian operators in asymptotic geometric analysis
- Metric and classical fidelity uncertainty relations for random unitary matrices
- Uniform estimates for order statistics and Orlicz functions
- Regularization and the small-ball method. II: Complexity dependent error rates
- Reconstructions that combine interpolation with least squares fitting
- Dvoretzky type theorems for subgaussian coordinate projections
- Robust high dimensional learning for Lipschitz and convex losses
- Discrepancy, chaining and subgaussian processes
- Random sections of _p-ellipsoids, optimal recovery and Gelfand numbers of diagonal operators
This page was built for publication: Gaussian averages of interpolated bodies and applications to approximate reconstruction
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2472364)
