Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
From MaRDI portal
Publication:428581
DOI10.1214/EJP.V16-958zbMATH Open1254.60014arXiv1103.3188MaRDI QIDQ428581FDOQ428581
Publication date: 22 June 2012
Published in: Electronic Journal of Probability (Search for Journal in Brave)
Abstract: We study the problem of non-asymptotic deviations between a reference measure and its empirical version, in the 1-Wasserstein metric, under the standing assumption that the measure satisfies a transport-entropy inequality. We extend some results of F. Bolley, A. Guillin and C. Villani with simple proofs. Our methods are based on concentration inequalities and extend to the general setting of measures on a Polish space. Deviation bounds for the occupation measure of a Markov chain are also given, under the assumption that the chain is contractive on the space of Lipschitz functions. Throughout the text, several examples are worked out, including the cases of Gaussian measures on separable Banach spaces, and laws of diffusion processes.
Full work available at URL: https://arxiv.org/abs/1103.3188
Convergence of probability measures (60B10) Inequalities; stochastic orderings (60E15) Systems of functional equations and inequalities (39B72)
Cited In (34)
- Sharp non-asymptotic concentration inequalities for the approximation of the invariant distribution of a diffusion
- Continuous limits of residual neural networks in case of large input data
- Non-asymptotic Gaussian estimates for the recursive approximation of the invariant distribution of a diffusion
- On the rate of convergence in Wasserstein distance of the empirical measure
- The Vlasov-Poisson dynamics as the mean field limit of extended charges
- Approximation of discounted minimax Markov control problems and zero-sum Markov games using Hausdorff and Wasserstein distances
- Empirical measures and random walks on compact spaces in the quadratic Wasserstein metric
- Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
- On the rate of convergence of empirical measure in $\infty $-Wasserstein distance for unbounded density function
- Uniform rates of the Glivenko-Cantelli convergence and their use in approximating Bayesian inferences
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- Long Time Results for a Weakly Interacting Particle System in Discrete Time
- Free transport-entropy inequalities for non-convex potentials and application to concentration for random matrices
- Computable approximations for continuous-time Markov decision processes on Borel spaces based on empirical measures
- Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities
- Complexity Reduction in Many Particle Systems with Random Initial Data
- Donsker theorems for occupation measures of multi-dimensional periodic diffusions
- One-dimensional empirical measures, order statistics, and Kantorovich transport distances
- Convergence of adapted empirical measures on \(\mathbb{R}^d\)
- A review of the mean field limits for Vlasov equations
- Deviation inequalities for separately Lipschitz functionals of iterated random functions
- On concentration of the empirical measure for radial transport costs
- On the trend to global equilibrium for Kuramoto oscillators
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
- Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- Discrete-time ergodic mean-field games with average reward on compact spaces
- Computable approximations for average Markov decision processes in continuous time
- Sharing the value‐at‐risk under distributional ambiguity
- A non-exponential extension of Sanov’s theorem via convex duality
- Stochastic approximations of constrained discounted Markov decision processes
- Data-driven inverse optimization with imperfect information
- Distribution dependent SDEs driven by additive continuous noise
- The spherical ensemble and quasi-Monte-Carlo designs
Recommendations
- On the rate of convergence in Wasserstein distance of the empirical measure 👍 👎
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance 👍 👎
- Mean rates of convergence of empirical measures in the Wasserstein metric 👍 👎
- Approximation rate in Wasserstein distance of probability measures on the real line by deterministic empirical measures 👍 👎
- Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces 👍 👎
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance 👍 👎
- On the rate of convergence of empirical measure in $\infty $-Wasserstein distance for unbounded density function 👍 👎
- Convergence in Wasserstein distance for empirical measures of Dirichlet diffusion processes on manifolds 👍 👎
- Convergence in Wasserstein distance for empirical measures of semilinear SPDEs 👍 👎
- Convergence of the empirical measure in expected wasserstein distance: non-asymptotic explicit bounds in ℝd 👍 👎
This page was built for publication: Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q428581)
