aiqbench analysis
This paper establishes a rigorous mathematical framework for proving the convergence of Markov chains by utilizing asymptotic equivalence criteria, specifically addressing Metropolis-Hastings algorithms and Gibbs samplers without relying on traditional assumptions like irreducibility or coupling. By verifying these conditions across general measurable spaces, the work provides essential theoretical guarantees for the strong law of large numbers in advanced sampling methods used throughout machine learning and statistical physics.
A Direct Route to Markov Chain Convergence via Asymptotic Equivalence with the Target
arXiv:2608.03353v1 Announce Type: cross Abstract: For a Markov kernel $T$ with an invariant probability measure $\pi$, we give a self-contained proof of the Markov chain convergence theorem via a criterion called asymptotic equivalence with the target. It assumes two parts about the Lebesgue decompositions of $T^{n}_{x}$ and $\pi$ for every starting point $x$: 1.) asymptotic absolute continuity: the singular mass sing$(T^{n}_{x}\mid\pi)$ tends to $0$; 2.) asymptotic domination of the target: the singular mass sing$(\pi\mid T^{n}_{x})$ tends to $0$, as $n \to \infty$. This criterion, on countably generated measurable spaces, is both sufficient and necessary for the Markov chain convergence. A density version of this criterion is verified on general measurable spaces in three cases: (i) $T$ has a positive transition density wrt $\pi$; (ii) $T$ consists of an absolutely continuous part with positive transition density together with an atom at the starting point, which covers the Metropolis--Hastings algorithm; (iii) the transition density is positive only after a finite number of steps that may depend on the starting point $x$. To demonstrate our general criterion, we investigate the Gibbs sampler with random scan and the parallel tempering algorithm. Furthermore, we show that in all mentioned settings Birkhoff's ergodic theorem applies, so as to obtain the strong law of large numbers. Throughout this paper, neither irreducibility, nor aperiodicity, nor recurrence, nor couplings, nor splitting constructions, nor small sets are used. In most results, the state space is a general measurable space, which carries no structure beyond a $\sigma$-algebra. Countable generation is only assumed where the density-free form of the criterion is stated. None of the theorems proved here is new; what is offered is a short route to a single, widely applicable Markov chain convergence criterion, which is both sufficient and necessary.
Abstract:For a Markov kernel $T$ with an invariant probability measure $\pi$, we give a self-contained proof of the Markov chain convergence theorem via a criterion called asymptotic equivalence with the target. It assumes two parts about the Lebesgue decompositions of $T^{n}_{x}$ and $\pi$ for every starting point $x$: 1.) asymptotic absolute continuity: the singular mass sing$(T^{n}_{x}\mid\pi)$ tends to $0$; 2.) asymptotic domination of the target: the singular mass sing$(\pi\mid T^{n}_{x})$ tends to $0$, as $n \to \infty$. This criterion, on countably generated measurable spaces, is both sufficient and necessary for the Markov chain convergence. A density version of this criterion is verified on general measurable spaces in three cases: (i) $T$ has a positive transition density wrt $\pi$; (ii) $T$ consists of an absolutely continuous part with positive transition density together with an atom at the starting point, which covers the Metropolis--Hastings algorithm; (iii) the transition density is positive only after a finite number of steps that may depend on the starting point $x$. To demonstrate our general criterion, we investigate the Gibbs sampler with random scan and the parallel tempering algorithm. Furthermore, we show that in all mentioned settings Birkhoff's ergodic theorem applies, so as to obtain the strong law of large numbers. Throughout this paper, neither irreducibility, nor aperiodicity, nor recurrence, nor couplings, nor splitting constructions, nor small sets are used. In most results, the state space is a general measurable space, which carries no structure beyond a $\sigma$-algebra. Countable generation is only assumed where the density-free form of the criterion is stated. None of the theorems proved here is new; what is offered is a short route to a single, widely applicable Markov chain convergence criterion, which is both sufficient and necessary.
Probability (math.PR); Machine Learning (cs.LG); Statistics Theory (math.ST); Computation (stat.CO); Machine Learning (stat.ML)
arXiv:2608.03353 [math.PR]
(or arXiv:2608.03353v1 [math.PR] for this version)
https://doi.org/10.48550/arXiv.2608.03353 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 389 words
Related coverage
The PPA: A New Approach to Anthropics
LessWrong · Oct 14, 2026
Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions
arXiv · Jun 10, 2026
Game Design Creativity evals
LessWrong · Oct 12, 2026
A Characterization of the Orthocomplement of the Tangent Space of Semiparametric Markov Models
arXiv · Jul 28, 2026