paper-with-me

홈 › Papers

Metrizing Weak Convergence with Maximum Mean Discrepancies

2020-06-16 · Carl-Johann Simon-Gabriel, Alessandro Barp, Bernhard Schölkopf, Lester Mackey

This paper characterizes the maximum mean discrepancies (MMD) that metrize the weak convergence of probability measures for a wide class of kernels. More precisely, we prove that, on a locally compact, non-compact, Hausdorff space, the MMD of a bounded continuous Borel measurable kernel k, whose reproducing kernel Hilbert space (RKHS) functions vanish at infinity, metrizes the weak convergence of probability measures if and only if k is continuous and integrally strictly positive definite (i.s.p.d.) over all signed, finite, regular Borel measures. We also correct a prior result of Simon-Gabriel & Sch\"olkopf (JMLR, 2018, Thm.12) by showing that there exist both bounded continuous i.s.p.d. kernels that do not metrize weak convergence and bounded continuous non-i.s.p.d. kernels that do metrize it.

📄 PDF Abstract BibTeX arXiv:2006.09268

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Maximum mean discrepancies of Farey sequences

2024-07-14 · Toni Karvonen, Anatoly Zhigljavsky

We identify a large class of positive-semidefinite kernels for which a certain polynomial rate of convergence of maximum mean discrepancies of Farey sequences is equivalent to the Riemann hypothesis. This class includes …

Targeted Separation and Convergence with Kernel Discrepancies

2022-09-26 · Alessandro Barp, Carl-Johann Simon-Gabriel, Mark Girolami, Lester Mackey

Maximum mean discrepancies (MMDs) like the kernel Stein discrepancy (KSD) have grown central to a wide range of applications, including hypothesis testing, sampler selection, distribution approximation, and variational i…

Variational Inference

Controlling Moments with Kernel Stein Discrepancies

2022-11-10 · Heishiro Kanagawa, Alessandro Barp, Arthur Gretton, Lester Mackey

Kernel Stein discrepancies (KSDs) measure the quality of a distributional approximation and can be computed even when the target density has an intractable normalizing constant. Notable applications include the diagnosis…

Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies

2026-03-02 · Lénaïc Chizat, Maria Colombo, Roberto Colombo, Xavier Fernández-Real arxiv

We study the quantitative convergence of Wasserstein gradient flows of Kernel Mean Discrepancy (KMD) (also known as Maximum Mean Discrepancy (MMD)) functionals. Our setting covers in particular the training dynamics of s…

Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow

2026-05-10 · Lénaïc Chizat, Maria Colombo, Roberto Colombo, Xavier Fernández-Real arxiv

Stein Variational Gradient Descent (SVGD) is a deterministic interacting-particle method for sampling from a target probability measure given access to its score function. In the mean-field and continuous-time limit, it …