English
Related papers

Related papers: Ballistic Convergence in Hit-and-Run Monte Carlo a…

200 papers

We propose the Hit-and-Run algorithm for planning and sampling problems in non-convex spaces. For sampling, we show the first analysis of the Hit-and-Run algorithm in non-convex spaces and show that it mixes fast as long as certain…

Computation · Statistics 2016-10-28 Yasin Abbasi-Yadkori , Peter L. Bartlett , Victor Gabillon , Alan Malek

We present a Hamiltonian Monte Carlo algorithm to sample from multivariate Gaussian distributions in which the target space is constrained by linear and quadratic inequalities or products thereof. The Hamiltonian equations of motion can be…

Computation · Statistics 2013-06-06 Ari Pakman , Liam Paninski

We establish the geometric ergodicity of the preconditioned Hamiltonian Monte Carlo (HMC) algorithm defined on an infinite-dimensional Hilbert space, as developed in [Beskos et al., Stochastic Process. Appl., 2011]. This algorithm can be…

Statistics Theory · Mathematics 2020-03-19 Nathan E. Glatt-Holtz , Cecilia F. Mondaini

Under mild assumptions, we show the exact convergence rate in total variation is also exact in weaker Wasserstein distances for the Metropolis-Hastings independence sampler. We develop a new upper and lower bound on the worst-case…

Statistics Theory · Mathematics 2022-11-15 Austin Brown , Galin L. Jones

Recent progress on the theory of variational hypocoercivity established that Randomized Hamiltonian Monte Carlo -- at criticality -- can achieve pronounced acceleration in its convergence and hence sampling performance over diffusive…

Statistics Theory · Mathematics 2025-07-18 Stefan Oberdörster

The Gibbs Sampler is a general method for sampling high-dimensional distributions, dating back to Turchin, 1971. In each step of the Gibbs Sampler, we pick a random coordinate and re-sample that coordinate from the distribution induced by…

Data Structures and Algorithms · Computer Science 2022-03-03 Aditi Laddha , Santosh Vempala

In this paper, we provide sufficient conditions for the existence of the invariant distribution and for subgeometric rates of convergence in Wasserstein distance for general state-space Markov chains which are (possibly) not irreducible.…

Probability · Mathematics 2015-07-15 Alain Durmus , Gersende Fort , Eric Moulines

We establish quantitative convergence rates for stochastic particle approximation based on Nanbu-type Monte Carlo schemes applied to a broad class of collisional kinetic models. Using coupling techniques and stability estimates in the…

Numerical Analysis · Mathematics 2025-04-15 Giacomo Borghi , Lorenzo Pareschi

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…

Probability · Mathematics 2023-09-19 Jiequn Han , Ruimeng Hu , Jihao Long

We study the problem of sampling from a distribution $\target$ using the Langevin Monte Carlo algorithm and provide rate of convergences for this algorithm in terms of Wasserstein distance of order $2$. Our result holds as long as the…

Computation · Statistics 2016-07-04 Thomas Bonis

The emergence of big data has led to a growing interest in so-called convergence complexity analysis, which is the study of how the convergence rate of a Monte Carlo Markov chain (for an intractable Bayesian posterior distribution) scales…

Statistics Theory · Mathematics 2021-08-12 Zhumengmeng Jin , James P. Hobert

We analyze the convergence rate of the randomized Newton-like method introduced by Qu et. al. (2016) for smooth and convex objectives, which uses random coordinate blocks of a Hessian-over-approximation matrix $\bM$ instead of the true…

Numerical Analysis · Mathematics 2020-02-13 Mojmír Mutný , Michał Dereziński , Andreas Krause

Existing rigorous convergence guarantees for the Hamiltonian Monte Carlo (HMC) algorithm use Gaussian auxiliary momentum variables, which are crucially symmetrically distributed. We present a novel convergence analysis for HMC utilizing new…

Machine Learning · Statistics 2026-05-12 Soumyadip Ghosh , Yingdong Lu , Tomasz Nowicki

We present a framework for obtaining explicit bounds on the rate of convergence to equilibrium of a Markov chain on a general state space, with respect to both total variation and Wasserstein distances. For Wasserstein bounds, our main tool…

Statistics Theory · Mathematics 2011-02-28 Neal Madras , Deniz Sezer

To conduct a more in-depth investigation of randomized solvers for solving linear systems, we adopt a unified randomized batch-sampling Kaczmarz framework with per-iteration costs as low as cyclic block methods, and develop a general…

Numerical Analysis · Mathematics 2026-04-21 Dong-Yue Xie , Xi Yang

The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational and statistical benefits. Since it is defined as an…

Machine Learning · Statistics 2022-01-05 Kimia Nadjahi , Alain Durmus , Pierre E. Jacob , Roland Badeau , Umut Şimşekli

Markov Chain Monte Carlo inference of target posterior distributions in machine learning is predominately conducted via Hamiltonian Monte Carlo and its variants. This is due to Hamiltonian Monte Carlo based samplers ability to suppress…

Machine Learning · Statistics 2021-07-06 Wilson Tsakane Mongwe , Rendani Mbuvha , Tshilidzi Marwala

We theoretically analyze the properties of a geodesic random walk on the Euclidean $d$-sphere. Specifically, we prove that the random walk's transition kernel is Wasserstein contractive with a contraction rate which can be bounded from…

Statistics Theory · Mathematics 2024-10-15 Philip Schär , Thilo D. Stier

The Wasserstein distance between two probability measures on a metric space is a measure of closeness with applications in statistics, probability, and machine learning. In this work, we consider the fundamental question of how quickly the…

Probability · Mathematics 2017-07-04 Jonathan Weed , Francis Bach

Sliced Wasserstein distances preserve properties of classic Wasserstein distances while being more scalable for computation and estimation in high dimensions. The goal of this work is to quantify this scalability from three key aspects: (i)…

Machine Learning · Statistics 2022-10-18 Sloan Nietert , Ritwik Sadhu , Ziv Goldfeld , Kengo Kato
‹ Prev 1 2 3 10 Next ›