Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.13916

Markov Chain Convergence in Kernel-Induced Geometry

Oleksii Kachaiev·Luc Brogat-Motte·Silvia Villa·Lorenzo Rosasco
View original source ↗Read source document ↗Export metadata ↓

Abstract

We study the convergence of Markov chains in the geometry induced by Hilbertian embeddings associated with positive definite kernels, also called Maximum Mean Discrepancy (MMD). Under a contraction assumption in the kernel-induced geometry, and a standard spectral gap assumption, we establish non-asymptotic, high-probability bounds for the convergence of the empirical occupation measure to the invariant measure. The obtained bounds separate the roles of the two conditions: the spectral gap determines the effective sample size in the leading term, while the kernel contraction enters only through a linear correction. As an application, we study one-step prediction of dynamical systems from a single trajectory, deriving fast learning rates for a nonlinear least-squares estimator. The rates highlight the interplay between mixing properties in the kernel-induced geometry and the classical source and capacity conditions used in the analysis of least-squares.

Explore related subjects

math.PRstat.ML

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Oleksii Kachaiev, Luc Brogat-Motte, Silvia Villa, Lorenzo Rosasco. 2026-10-09. Markov Chain Convergence in Kernel-Induced Geometry. https://arxiv.org/abs/2610.13916

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Large deviation principle at speed $n^d$ for the random metric in first-passage percolation

We consider the standard first passage percolation model on $\mathbb Z^d$ with bounded weights. We show a large deviation estimate for the probability that the rescaled passage time restricted to a box is greater than a target pseudometric. Moreover, the associated rate function can be written as the integral over the box of an elementary cost. Under the additional assumption that weights are bounded away from zero, the random pseudometric follows a large deviation principle (LDP) at speed $n^d$. Consequences include LDPs at speed $n^d$ for the point-to-point passage time, the crossing passage time and the random ball of radius $n$. Our strategy consists in proving first the existence of the rate function for any seminorm $g$ with a multidimensional subadditivity argument, then using this result as an elementary building block to estimate the rate function in full generality.

math.PR↗
arXiv2026

On the Kantorovich contraction of Markov semigroups

We develop an operator-theoretic framework for the contraction properties of Markov semigroups with respect to a general class of Kantorovich semi-distances, which includes Wasserstein distances and weighted total variation norms. The framework is based on Kantorovich contraction coefficients, which extend Dobrushin's ergodic coefficient from the total variation distance to general transport costs. Our main result shows that a geometric drift condition, combined with a local contraction condition on the sub-level sets of the Lyapunov function, implies that the Markov operator is a strict contraction with respect to an explicit modification of the underlying Kantorovich cost. This yields, in a unified way, the existence and uniqueness of invariant measures and exponential decay estimates in Wasserstein distances, for both discrete time and continuous time Markov semigroups, as well as for time-varying semigroups. We illustrate the scope of the framework with (i) Markov transitions on models with boundary states, including bounded domains with entrance boundaries, (ii) operator products of a Markov kernel and its adjoint, including two-block Gibbs samplers, (iii) iterated random functions, including Euler-type schemes, (iv) diffusion models, including overdamped Langevin diffusions with potentials that are convex at infinity, jump-diffusions on compact manifolds, and Jacobi and Riccati matrix diffusions, and (v) time-varying and nonlinear semigroups, including Feynman-Kac distribution flows and Sinkhorn bridges. In several of these settings we obtain new contraction estimates, while in others we recover known results through short and elementary arguments.

math.PR↗
arXiv2026

Sharpness of the percolation phase transition for weighted random connection models

We establish the sharpness of the percolation phase transition for a class of potentially infinite-range weighted random connection models. The vertex set is given by a marked Poisson point process on $\mathbb R^d$, $d\geq 2$, with intensity $λ>0$, where each vertex carries an independent weight. Given a pair of vertices, an edge is drawn independently with a probability that depends on both their spatial displacement and their respective weights. Our geometric and moment assumptions allow the expected degree to be unbounded over the weights. We prove exponential tails for the number of vertices in the root cluster throughout the subcritical regime. We also obtain a linear lower bound on the percolation probability near criticality from above. The class of systems considered includes min-reach models, Poisson--Boolean overlap models, and suitable softened versions thereof. Our proof combines a finite-volume lattice approximation with Hutchcroft's exploration approach to the OSSS inequality.

math.PR↗