A Class of Dimension-free Metrics for the Convergence of Empirical Measures

• URL: http://arxiv.org/abs/2104.12036v4
• Date: Sat, 16 Sep 2023 22:08:35 GMT
• Title: A Class of Dimension-free Metrics for the Convergence of Empirical Measures
• Authors: Jiequn Han, Ruimeng Hu, Jihao Long
• Abstract summary: We show that under the proposed metrics, the convergence of empirical measures in high dimensions is free of the curse of dimensionality (CoD) Examples of selected test function spaces include the kernel reproducing Hilbert spaces, Barron space, and flow-induced function spaces. We show that the proposed class of metrics is a powerful tool to analyze the convergence of empirical measures in high dimensions without CoD.
• Score: 6.253771639590562
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper concerns the convergence of empirical measures in high dimensions. We propose a new class of probability 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 metric). The proposed metrics fall into the category of integral probability metrics, for which we specify criteria of test function spaces to guarantee the property of being free of CoD. Examples of the selected test function spaces include the reproducing kernel Hilbert spaces, 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 our metric and a certain representation of the target distribution, we can generate a distribution close to the target one in terms of the Wasserstein metric 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.

Related papers

• Intrinsic Bayesian Cramér-Rao Bound with an Application to Covariance Matrix Estimation [49.67011673289242]
  This paper presents a new performance bound for estimation problems where the parameter to estimate lies in a smooth manifold. It induces a geometry for the parameter manifold, as well as an intrinsic notion of the estimation error measure.
  arXiv  Detail & Related papers  (2023-11-08T15:17:13Z)
• A High-dimensional Convergence Theorem for U-statistics with Applications to Kernel-based Testing [3.469038201881982]
  We prove a convergence theorem for U-statistics of degree two, where the data dimension $d$ is allowed to scale with sample size $n$. We apply our theory to two popular kernel-based distribution tests, MMD and KSD, whose high-dimensional performance has been challenging to study.
  arXiv  Detail & Related papers  (2023-02-11T12:49:46Z)
• Targeted Separation and Convergence with Kernel Discrepancies [61.973643031360254]
  kernel-based discrepancy measures are required to (i) separate a target P from other probability measures or (ii) control weak convergence to P. In this article we derive new sufficient and necessary conditions to ensure (i) and (ii) For MMDs on separable metric spaces, we characterize those kernels that separate Bochner embeddable measures and introduce simple conditions for separating all measures with unbounded kernels.
  arXiv  Detail & Related papers  (2022-09-26T16:41:16Z)
• Nonlinear Sufficient Dimension Reduction for Distribution-on-Distribution Regression [9.086237593805173]
  We introduce a new approach to nonlinear sufficient dimension reduction in cases where both the predictor and the response are distributional data. Our key step is to build universal kernels (cc-universal) on the metric spaces.
  arXiv  Detail & Related papers  (2022-07-11T04:11:36Z)
• Dimension Reduction and Data Visualization for Fr\'echet Regression [8.713190936209156]
  Fr'echet regression model provides a promising framework for regression analysis with metric spacevalued responses. We introduce a flexible sufficient dimension reduction (SDR) method for Fr'echet regression to achieve two purposes.
  arXiv  Detail & Related papers  (2021-10-01T15:01:32Z)
• A Note on Optimizing Distributions using Kernel Mean Embeddings [94.96262888797257]
  Kernel mean embeddings represent probability measures by their infinite-dimensional mean embeddings in a reproducing kernel Hilbert space. We show that when the kernel is characteristic, distributions with a kernel sum-of-squares density are dense. We provide algorithms to optimize such distributions in the finite-sample setting.
  arXiv  Detail & Related papers  (2021-06-18T08:33:45Z)
• A Unifying and Canonical Description of Measure-Preserving Diffusions [60.59592461429012]
  A complete recipe of measure-preserving diffusions in Euclidean space was recently derived unifying several MCMC algorithms into a single framework. We develop a geometric theory that improves and generalises this construction to any manifold.
  arXiv  Detail & Related papers  (2021-05-06T17:36:55Z)
• Metrizing Weak Convergence with Maximum Mean Discrepancies [88.54422104669078]
  This paper characterizes the maximum mean discrepancies (MMD) that metrize the weak convergence of probability measures for a wide class of kernels. We prove that, on a locally compact, non-compact, Hausdorff space, the MMD of a bounded continuous Borel measurable kernel k, metrizes the weak convergence of probability measures if and only if k is continuous.
  arXiv  Detail & Related papers  (2020-06-16T15:49:33Z)
• Entanglement distance for arbitrary $M$-qudit hybrid systems [0.0]
  We propose a measure of entanglement which can be computed for pure and mixed states of a $M$-qudit hybrid system. We quantify the robustness of entanglement of a state through the eigenvalues analysis of the metric tensor associated with it.
  arXiv  Detail & Related papers  (2020-03-11T15:16:36Z)
• Generalized Sliced Distances for Probability Distributions [47.543990188697734]
  We introduce a broad family of probability metrics, coined as Generalized Sliced Probability Metrics (GSPMs) GSPMs are rooted in the generalized Radon transform and come with a unique geometric interpretation. We consider GSPM-based gradient flows for generative modeling applications and show that under mild assumptions, the gradient flow converges to the global optimum.
  arXiv  Detail & Related papers  (2020-02-28T04:18:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.