Sanov's theorem in the Wasserstein distance: a necessary and sufficient condition

DOI10.1016/j.spl.2009.12.003zbMath1186.60024OpenAlexW2008872040MaRDI QIDQ2267634

Ran Wang, Li-ming Wu, Xin Yu Wang

Publication date: 1 March 2010

Published in: Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.spl.2009.12.003

zbMATH Keywords

Wasserstein metriclarge deviation principleSanov's theorem

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Large deviations (60F10)

Related Items

Equilibrium large deviations for mean-field systems with translation invariance ⋮ The enhanced Sanov theorem and propagation of chaos ⋮ Nonexponential Sanov and Schilder theorems on Wiener space: BSDEs, Schrödinger problems and control ⋮ Pathwise McKean-Vlasov theory with additive noise ⋮ Data-Driven Optimization of Reward-Risk Ratio Measures ⋮ Large deviations for configurations generated by Gibbs distributions with energy functionals consisting of singular interaction and weakly confining potentials ⋮ From the master equation to mean field game limit theory: large deviations and concentration of measure ⋮ Large deviations and gradient flows for the Brownian one-dimensional hard-rod system ⋮ Limit theorems for Fréchet mean sets ⋮ Bayesian learning with Wasserstein barycenters ⋮ Large deviation principles induced by the Stiefel manifold, and random multidimensional projections ⋮ The mean field Schrödinger problem: ergodic behavior, entropy estimates and functional inequalities ⋮ A conditional limit theorem for high-dimensional ℓᵖ-spheres ⋮ Asymptotic behavior of the empirical conditional value-at-risk ⋮ First-order global asymptotics for confined particles with singular pair repulsion ⋮ A non-exponential extension of Sanov’s theorem via convex duality ⋮ Large deviations of empirical measures of diffusions in weighted topologies ⋮ Large deviations for empirical measures of mean-field Gibbs measures ⋮ An asymptotic thin shell condition and large deviations for random multidimensional projections ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Quantitative concentration inequalities for empirical measures on non-compact spaces
• Large deviations, moderate deviations and LIL for empirical processes
• Exponential approximations in completely regular topological spaces and extensions of Sanov's theorem
• A large deviation approach to some transportation cost inequalities
• Large Deviations Principle for Partial Sums U-Processes
• Optimal Transport