On Choosing and Bounding Probability Metrics
From MaRDI portal
Publication:4832030
DOI10.2307/1403865zbMATH Open1217.62014OpenAlexW2951714068MaRDI QIDQ4832030FDOQ4832030
Authors: Alison L. Gibbs, Francis Edward Su 
Publication date: 3 January 2005
Published in: International Statistical Review / Revue Internationale de Statistique (Search for Journal in Brave)
Abstract: When studying convergence of measures, an important issue is the choice of probability metric. In this review, we provide a summary and some new results concerning bounds among ten important probability metrics/distances that are used by statisticians and probabilists. We focus on these metrics because they are either well-known, commonly used, or admit practical bounding techniques. We summarize these relationships in a handy reference diagram, and also give examples to show how rates of convergence can depend on the metric chosen.
Full work available at URL: https://arxiv.org/abs/math/0209021
Recommendations
Convergence of probability measures (60B10) Characterization and structure theory of statistical distributions (62E10) Statistical distribution theory (62E99)
Cited In (only showing first 100 items - show all)
- On emergence and complexity of ergodic decompositions
- Cut-off for \(n\)-tuples of exponentially converging processes
- Lack of phase transitions in staggered magnetic systems. A comparison of uniqueness criteria
- Dirichlet is natural
- Computationally tractable counterparts of distributionally robust constraints on risk measures
- Risk-averse two-stage stochastic program with distributional ambiguity
- A quantitative discounted central limit theorem using the Fourier metric
- Centered Sobolev inequality and exponential convergence in \(\Phi\)-entropy
- Robust sample average approximation
- Compound Poisson approximation
- On robust portfolio and naïve diversification: mixing ambiguous and unambiguous assets
- Quantitative stability analysis of stochastic mathematical programs with vertical complementarity constraints
- Peacocks nearby: approximating sequences of measures
- A Monte Carlo approach to quantifying model error in Bayesian parameter estimation
- Asymptotics of one-dimensional Lévy approximations
- Equidistribution for nonuniformly expanding dynamical systems, and application to the almost sure invariance principle
- Nonlinear nonparametric mixed-effects models for unsupervised classification
- A framework for optimization under ambiguity
- Fuzzy clustering of distributional data with automatic weighting of variable components
- A note on the chi-square method: a tool for proving cryptographic security
- Convergence analysis for mathematical programs with distributionally robust chance constraint
- Analysis of the ensemble and polynomial chaos Kalman filters in Bayesian inverse problems
- Some inequalities for Csiszár divergence via theory of time scales
- Weak and TV consistency in Bayesian uncertainty quantification using disintegration
- Ordinary least squares for histogram data based on Wasserstein distance
- Wasserstein distance and the distributionally robust TSP
- Decomposition and discrete approximation methods for solving two-stage distributionally robust optimization problems
- An emergent autonomous flow for mean-field spin glasses
- Generalization of some bounds containing entropies on time scales
- Levinson-type inequalities via new Green functions and Montgomery identity
- Weak solutions of mean-field stochastic differential equations and application to zero-sum stochastic differential games
- A density-matching approach for optimization under uncertainty
- Stochastic gradient Markov chain Monte Carlo
- On generalization in moment-based domain adaptation
- A probabilistic numerical method for a class of mean field games
- Implicit sampling for hierarchical Bayesian inversion and applications in fractional multiscale diffusion models
- Metrics on trace spaces
- On the robustness of randomized classifiers to adversarial examples
- A characterization of \(L_{2}\) mixing and hypercontractivity via hitting times and maximal inequalities
- On the rate of convergence in de Finetti's representation theorem
- THE PROPERTIES OF KULLBACK–LEIBLER DIVERGENCE FOR THE UNIT ROOT HYPOTHESIS
- Importance Sampling and Necessary Sample Size: An Information Theory Approach
- Correspondence analysis and the Freeman-Tukey statistic: a study of archaeological data
- Long-term values in Markov decision processes, (co)algebraically
- Local modulated wave model for the reconstruction of space-time energy spectra in turbulent flows
- Families of well approximable measures
- Bounds on lifting continuous-state Markov chains to speed up mixing
- The Fleming-Viot process with McKean-Vlasov dynamics
- Some remarks on Bayesian multiple hypothesis testing
- A theoretical examination of diffusive molecular dynamics
- A central limit theorem, and related results, for a two-color randomly reinforced urn
- On the relationship between bisimulation and trace equivalence in an approximate probabilistic context
- Concentration inequalities for kernel density estimators under uniform mixing
- Two-sample Kolmogorov-Smirnov test using a Bayesian nonparametric approach
- Analysis of interspike-intervals for the general class of integrate-and-fire models with periodic drive
- Stabilizing Invertible Neural Networks Using Mixture Models
- On the local Lipschitz stability of Bayesian inverse problems
- Multiple-source adaptation theory and algorithms
- Synchronization and functional central limit theorems for interacting reinforced random walks
- Bayesian consistency for a nonparametric stationary Markov model
- Mathematical foundation of the replicating portfolio approach
- Best finite approximations of Benford's law
- Accelerating Markov chain Monte Carlo with active subspaces
- Transport map accelerated Markov chain Monte Carlo
- On distributionally robust optimization problems with \(k\)-th order stochastic dominance constraints induced by full random quadratic recourse
- An information theoretic approach to post randomization methods under differential privacy
- Stein's method for the single server queue in heavy traffic
- The pure exploration problem with general reward functions depending on full distributions
- Improved inference for vaccine-induced immune responses via shape-constrained methods
- Rate of convergence to the Circular Law via smoothing inequalities for log-potentials
- Insurance premium-based shortfall risk measure induced by cumulative prospect theory
- Robustly complete finite-state abstractions for verification of stochastic systems
- Likelihood estimation of sparse topic distributions in topic models and its applications to Wasserstein document distance calculations
- An integrated consensus improving strategy based on PL-Wasserstein distance and its application in the evaluation of network public opinion emergencies
- Discrete approximation and quantification in distributionally robust optimization
- Extended Laplace principle for empirical measures of a Markov chain
- Linear convergence of accelerated conditional gradient algorithms in spaces of measures
- Sparse inverse problems over measures: equivalence of the conditional gradient and exchange methods
- Posterior asymptotics in Wasserstein metrics on the real line
- Non-asymptotic error estimates for the Laplace approximation in Bayesian inverse problems
- Impossible inference in econometrics: theory and applications
- Spectral convergence of probability densities for forward problems in uncertainty quantification
- An information-theoretic framework for improving imperfect dynamical predictions via multi-model ensemble forecasts
- A note on distances between probabilistic and quantum distributions
- Title not available (Why is that?)
- Solving inverse problems in stochastic models using deep neural networks and adversarial training
- Graphop mean-field limits for Kuramoto-type models
- Optimal \(L_2\)-norm empirical importance weights for the change of probability measure
- Piecewise linear approximation of empirical distributions under a Wasserstein distance constraint
- A load balancing system in the many-server heavy-traffic asymptotics
- Batch self-organizing maps for distributional data with an automatic weighting of variables and components
- Bounds for the asymptotic distribution of the likelihood ratio
- On a new class of multivariate prior distributions: theory and application in reliability
- Phase transitions for detecting latent geometry in random graphs
- Generalization of the Levinson inequality with applications to information theory
- Estimation of \(f\)-divergence and Shannon entropy by Levinson-type inequalities via new Green's functions and Lidstone polynomial
- The computational asymptotics of Gaussian variational inference and the Laplace approximation
- Emergence of the wrapped Cauchy distribution in mixed directional data
- Isometries of probability measures with respect to the total variation distance
- On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems
This page was built for publication: On Choosing and Bounding Probability Metrics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4832030)
