Constructive quantization: approximation by empirical measures
From MaRDI portal
Abstract: In this article, we study the approximation of a probability measure on by its empirical measure interpreted as a random quantization. As error criterion we consider an averaged -th moment Wasserstein metric. In the case where , we establish refined upper and lower bounds for the error, a high-resolution formula. Moreover, we provide a universal estimate based on moments, a so-called Pierce type estimate. In particular, we show that quantization by empirical measures is of optimal order under weak assumptions.
The authors investigate the approximation of a probability measure \(\mu\) on \(\mathbb{R}^d\), \(d \geq 3\), by its empirical measure w.r.t. the minimal \(L_p\)-metric (\(L_p\)-Wasserstein metric). For \(p \in [1, \frac{1}{d})\) and finite absolute \(q\)-th order moment \(\mu_q\) of \(\mu\) they establish an upper bound of the order of the form \( \kappa \, \mu_q \, N^{-1/d}\), a so-called Pierce type estimate. For the uniform distribution on \([0,1)^d\) they obtain an exact limit theorem of order \(N^{-1/d}\) and establish a corresponding limit result for the optimal quantization by \(N\) points. Further it is shown that the order of quantization by empirical measures is optimal under weak distributional assumptions.
Recommendations
- Quantization for probability measures in the Prokhorov metric
- Foundations of quantization for probability distributions
- Approximation rate in Wasserstein distance of probability measures on the real line by deterministic empirical measures
- Quantization of probability distributions under norm-based distortion measures
- Optimal approximation and quantisation
Cites work
- A space quantization method for numerical integration
- Asymptotic formulae for coding problems and intermediate optimization problems: a review
- Asymptotically optimal quantization schemes for Gaussian processes on Hilbert spaces
- Asymptotics for transportation cost in high dimensions
- Combinatorial Optimization Over Two Random Point Sets
- Derandomization of the Euler scheme for scalar stochastic differential equations
- Foundations of quantization for probability distributions
- scientific article; zbMATH DE number 3134565 (Why is no real title available?)
- scientific article; zbMATH DE number 5010399 (Why is no real title available?)
- scientific article; zbMATH DE number 3664138 (Why is no real title available?)
- scientific article; zbMATH DE number 467196 (Why is no real title available?)
- scientific article; zbMATH DE number 3193293 (Why is no real title available?)
- Mean rates of convergence of empirical measures in the Wasserstein metric
- Multidimensional asymptotic quantization theory with<tex>r</tex>th power distortion measures
- On optimal matchings
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
- Optimal Delaunay and Voronoi quantization schemes for pricing American style options
- Optimal quadratic quantization for numerics: the Gaussian case
- Optimal transport from Lebesgue to Poisson
- Quantization of probability distributions under norm-based distortion measures
- The high resolution vector quantization problem with Orlicz norm distortion
- The transportation cost from the uniform measure to the empirical measure in dimension \(\geq 3\)
Cited in
(88)- Behavior of the empirical Wasserstein distance in \({\mathbb R}^d\) under moment conditions
- Random bit quadrature and approximation of distributions on Hilbert spaces
- Wasserstein upper bounds of the total variation for smooth densities
- Some results on the optimal matching problem for the Jacobi model
- A simple Fourier analytic proof of the AKT optimal matching theorem
- Convex order, quantization and monotone approximations of ARCH models
- A measure theoretical approach to the mean-field maximum principle for training NeurODEs
- Distribution dependent SDEs driven by additive continuous noise
- On the quadratic random matching problem in two-dimensional domains
- A fluctuation result for the displacement in the optimal matching problem
- Convergence of asymptotic costs for random Euclidean matching problems
- Measure estimation on manifolds: an optimal transport approach
- Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
- Weak quantitative propagation of chaos via differential calculus on the space of measures
- Asymptotics of one-dimensional Lévy approximations
- On quantitative stability in infinite-dimensional optimization under uncertainty
- Posterior asymptotics in Wasserstein metrics on the real line
- Antithetic multilevel sampling method for nonlinear functionals of measure
- Improved rates for Wasserstein deconvolution with ordinary smooth error in dimension one
- Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces
- Characterization of probability distribution convergence in Wasserstein distance by \(L^p\)-quantization error function
- On optimal matching of Gaussian samples
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- Uniform rates of the Glivenko-Cantelli convergence and their use in approximating Bayesian inferences
- Finer estimates on the 2-dimensional matching problem
- A gradient flow perspective on the quantization problem
- Best finite constrained approximations of one-dimensional probabilities
- A local refinement strategy for constructive quantization of scalar SDEs
- Estimation of Wasserstein distances in the spiked transport model
- Rate of convergence of the Nanbu particle system for hard potentials and Maxwell molecules
- A consistency estimate for Kac's model of elastic collisions in a dilute gas
- Inferring interaction rules from observations of evolutive systems I: The variational approach
- Consistency of probability measure quantization by means of power repulsion-attraction potentials
- Rates of convergence for robust geometric inference
- The Vlasov-Poisson dynamics as the mean field limit of extended charges
- Quantization for probability measures in the Prokhorov metric
- Derandomization of the Euler scheme for scalar stochastic differential equations
- Uniform decomposition of probability measures: quantization, clustering and rate of convergence
- Deviation inequalities for separately Lipschitz functionals of iterated random functions
- On the rate of convergence in Wasserstein distance of the empirical measure
- Dynamics of data-driven ambiguity sets for hyperbolic conservation laws with uncertain inputs
- Learning finite-dimensional coding schemes with nonlinear reconstruction maps
- On optimal matching of Gaussian samples. III
- Asymptotics for semidiscrete entropic optimal transport
- Randomized Wasserstein barycenter computation: resampling with statistical guarantees
- k-variance: a clustered notion of variance
- Empirical measures: regularity is a counter-curse to dimensionality
- One-dimensional empirical measures, order statistics, and Kantorovich transport distances
- Optimal Matching of Random Samples and Rates of Convergence of Empirical Measures
- The Convergence Problem in Mean Field Games with Neumann Boundary Conditions
- An Integrated Transportation Distance between Kernels and Approximate Dynamic Risk Evaluation in Markov Systems
- Master Bellman equation in the Wasserstein space: Uniqueness of viscosity solutions
- The Wasserstein distance to the circular law
- Mini-Batch Risk Forms
- Geometrical Insights for Implicit Generative Modeling
- Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
- Optimal transport methods for combinatorial optimization over two random point sets
- Wasserstein upper bounds of L^p-norms for multivariate densities in Besov spaces
- Limit distribution theory for smooth \(p\)-Wasserstein distances
- Empirical optimal transport between different measures adapts to lower complexity
- Convergence of adapted empirical measures on \(\mathbb{R}^d\)
- Gromov-Wasserstein distances: entropic regularization, duality and sample complexity
- Asymptotic properties of Monte Carlo methods in elliptic PDE-constrained optimization under uncertainty
- On the optimal rate for the convergence problem in mean field control
- On concentration of the empirical measure for radial transport costs
- Optimal matching problem on the Boolean cube
- Asymptotics of the quantization problem on metric measure spaces
- Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities
- Convergence of adapted smoothed empirical measures
- Two-sample distribution tests in high dimensions via max-sliced Wasserstein distance and bootstrapping
- Uniform in time weak propagation of chaos on the torus
- Distributionally robust optimization
- Asymptotics of Kantorovich distance for empirical measures of the Laguerre model
- Convergence of empirical optimal transport in unbounded settings
- Asymptotic quantization of measures on Riemannian manifolds via covering growth estimates
- Unbalanced Kantorovich-Rubinstein distance, plan, and barycenter on finite spaces: a statistical perspective
- Strategies with minimal norm are optimal for expected utility maximisation under high model ambiguity
- The distributionally robust prediction error of the \(\sqrt{\mathrm{LASSO}}\) and related estimators
- Approximate Bayesian Computation with Deep Learning and Conformal prediction
- Sharp convergence rates of empirical unbalanced optimal transport for spatio-temporal point processes
- Max-sliced Wasserstein concentration and uniform ratio bounds of empirical measures on RKHS
- Error estimates for deterministic empirical approximations of probability measures
- On the convergence of the Euler-Maruyama scheme for McKean-Vlasov SDEs
- Robust point matching with distance profiles
- Almost sharp rates of convergence for the average cost and displacement in the optimal matching problem
- Rate of convergence of the smoothed empirical Wasserstein distance
- Transport inequalities on Euclidean spaces for non-Euclidean metrics
- Optimal approximation and quantisation
This page was built for publication: Constructive quantization: approximation by empirical measures
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q376699)
