A class of dimension-free metrics for the convergence of empirical measures

DOI10.1016/J.SPA.2023.07.009zbMATH Open1522.60015arXiv2104.12036OpenAlexW4384700180MaRDI QIDQ6072907FDOQ6072907

Authors: Jiequn Han, Ruimeng Hu, Jihao Long 

Publication date: 15 September 2023

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Abstract: This paper concerns the convergence of empirical measures in high dimensions. We propose a new class of metrics and show that under such metrics, the convergence is free of the curse of dimensionality (CoD). Such a feature is critical for high-dimensional analysis and stands in contrast to classical metrics ({it e.g.}, the Wasserstein distance). The proposed metrics originate from the maximum mean discrepancy, which we generalize by proposing specific criteria for selecting test function spaces to guarantee the property of being free of CoD. Therefore, we call this class of metrics the generalized maximum mean discrepancy (GMMD). Examples of the selected test function spaces include the reproducing kernel Hilbert space, Barron space, and flow-induced function spaces. Three applications of the proposed metrics are presented: 1. The convergence of empirical measure in the case of random variables; 2. The convergence of $n$-particle system to the solution to McKean-Vlasov stochastic differential equation; 3. The construction of an $varepsilon$-Nash equilibrium for a homogeneous $n$-player game by its mean-field limit. As a byproduct, we prove that, given a distribution close to the target distribution measured by GMMD and a certain representation of the target distribution, we can generate a distribution close to the target one in terms of the Wasserstein distance and relative entropy. Overall, we show that the proposed class of metrics is a powerful tool to analyze the convergence of empirical measures in high dimensions without CoD.

Full work available at URL: https://arxiv.org/abs/2104.12036

Recommendations

• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces
• The CLT in high dimensions: quantitative bounds via martingale embedding
• A new framework for distance and kernel-based metrics in high dimensions
• Empirical measures: regularity is a counter-curse to dimensionality

zbMATH Keywords

curse of dimensionalitymean-field gamesempirical measureintegral probability metricsMckean-Vlasov stochastic differential equation

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Inequalities; stochastic orderings (60E15) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Mean field games (aspects of game theory) (91A16)

Cites Work

• Universal approximation bounds for superpositions of a sigmoidal function
• Theory of Reproducing Kernels
• Some results on Tchebycheffian spline functions and stochastic processes
• Title not available (Why is that?)
• Integral Probability Metrics and Their Generating Classes of Functions
• High-dimensional probability. An introduction with applications in data science
• Hanson-Wright inequality and sub-Gaussian concentration
• Kernel methods in machine learning
• Understanding machine learning. From theory to algorithms
• Title not available (Why is that?)
• Mean field games
• Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
• Probabilistic analysis of mean-field games
• 10.1162/153244303321897690
• Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized $\varepsilon$-Nash Equilibria
• A CLASS OF MARKOV PROCESSES ASSOCIATED WITH NONLINEAR PARABOLIC EQUATIONS
• The Speed of Mean Glivenko-Cantelli Convergence
• Mean field games. I: The stationary case
• Mean field games. II: Finite horizon and optimal control
• On the rate of convergence in Wasserstein distance of the empirical measure
• Title not available (Why is that?)
• Title not available (Why is that?)
• Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
• On the moments of the modulus of continuity of Itô processes
• Functional analysis. Introduction to further topics in analysis
• Transport Inequalities. A Survey
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Advanced Lectures on Machine Learning
• Probability Metrics
• Liquidity, risk measures, and concentration of measure
• Combinatorics of random processes and sections of convex bodies
• Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games
• Some stochastic particle methods for nonlinear parabolic PDEs
• On a strong form of propagation of chaos for McKean-Vlasov equations
• Probabilistic theory of mean field games with applications II. Mean field games with common noise and master equations
• Backward stochastic differential equations. From linear to fully nonlinear theory
• A priori estimates of the population risk for two-layer neural networks
• A mean field view of the landscape of two-layer neural networks
• Mean field analysis of neural networks: a law of large numbers
• Deep fictitious play for stochastic differential games
• From the master equation to mean field game limit theory: large deviations and concentration of measure
• Generalization error of GAN from the discriminator's perspective
• Kolmogorov width decay and poor approximators in machine learning: shallow neural networks, random feature models and neural tangent kernels
• Propagation of chaos: a review of models, methods and applications. I: Models and methods
• Simulation of McKean-Vlasov SDEs with super-linear growth
• The Barron space and the flow-induced function spaces for neural network models
• Convergence of deep fictitious play for stochastic differential games

Cited In (2)

• Learning High-Dimensional McKean–Vlasov Forward-Backward Stochastic Differential Equations with General Distribution Dependence
• Recent developments in machine learning methods for stochastic control and games

This page was built for publication: A class of dimension-free metrics for the convergence of empirical measures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6072907)