中文
相关论文

相关论文: On log-concave approximations of high-dimensional …

200 篇论文

Non-convex sampling is a key challenge in machine learning, central to non-convex optimization in deep learning as well as to approximate probabilistic inference. Despite its significance, theoretically there remain many important…

机器学习 · 计算机科学 2024-09-18 Mohammad Reza Karimi , Ya-Ping Hsieh , Andreas Krause

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…

统计计算 · 统计学 2016-07-04 Thomas Bonis

In this note we consider the stability of posterior measures occuring in Bayesian inference w.r.t. perturbations of the prior measure and the log-likelihood function. This extends the well-posedness analysis of Bayesian inverse problems. In…

统计理论 · 数学 2020-06-24 Björn Sprungk

Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling…

统计计算 · 统计学 2016-12-06 Arnak S. Dalalyan

In this paper, we revisit the recently established theoretical guarantees for the convergence of the Langevin Monte Carlo algorithm of sampling from a smooth and (strongly) log-concave density. We improve the existing results when the…

统计理论 · 数学 2017-07-31 Arnak S. Dalalyan

We derive first-order (in the stepsize) bounds on the bias in Wasserstein distances of the invariant measure of stochastic gradient kinetic Langevin dynamics with minimal assumptions on the stochastic gradient noise. These bounds sharpen…

统计计算 · 统计学 2026-04-28 Daniel Paulin , Peter A. Whalley

It is well-known that the posterior density of linear inverse problems with Gaussian prior and Gaussian likelihood is also Gaussian, hence completely described by its covariance and expectation. Sampling from a Gaussian posterior may be…

数值分析 · 数学 2025-02-11 Daniela Calvetti , Erkki Somersalo

Recently, Approximate Message Passing (AMP) has been integrated with stochastic localization (diffusion model) by providing a computationally efficient estimator of the posterior mean. Existing (rigorous) analysis typically proves the…

统计理论 · 数学 2025-03-18 Han Cui , Zhiyuan Yu , Jingbo Liu

In this paper, we study the problem of sampling from a given probability density function that is known to be smooth and strongly log-concave. We analyze several methods of approximate sampling based on discretizations of the (highly…

统计理论 · 数学 2024-02-26 Arnak S. Dalalyan , Avetik G. Karagulyan

We present a framework that allows for the non-asymptotic study of the $2$-Wasserstein distance between the invariant distribution of an ergodic stochastic differential equation and the distribution of its numerical approximation in the…

机器学习 · 统计学 2021-09-27 J. M. Sanz-Serna , Konstantinos C. Zygalakis

Solutions to inverse problems that are ill-conditioned or ill-posed may have significant intrinsic uncertainty. Unfortunately, analysing and quantifying this uncertainty is very challenging, particularly in high-dimensional problems. As a…

统计方法学 · 统计学 2016-07-12 Marcelo Pereyra

The problem of generating random samples of high-dimensional posterior distributions is considered. The main results consist of non-asymptotic computational guarantees for Langevin-type MCMC algorithms which scale polynomially in key…

统计理论 · 数学 2022-03-25 Richard Nickl , Sven Wang

Two major bottlenecks to the solution of large-scale Bayesian inverse problems are the scaling of posterior sampling algorithms to high-dimensional parameter spaces and the computational cost of forward model evaluations. Yet incomplete or…

统计计算 · 统计学 2016-05-03 Tiangang Cui , Youssef M. Marzouk , Karen E. Willcox

Discretized Langevin diffusions are efficient Monte Carlo methods for sampling from high dimensional target densities that are log-Lipschitz-smooth and (strongly) log-concave. In particular, the Euclidean Langevin Monte Carlo sampling…

统计理论 · 数学 2020-02-12 Kelvin Shuangjian Zhang , Gabriel Peyré , Jalal Fadili , Marcelo Pereyra

Contraction in Wasserstein 1-distance with explicit rates is established for generalized Hamiltonian Monte Carlo with stochastic gradients under possibly nonconvex conditions. The algorithms considered include splitting schemes of kinetic…

概率论 · 数学 2024-09-16 Martin Chak , Pierre Monmarché

Inverse problems in physical or biological sciences often involve recovering an unknown parameter that is random. The sought-after quantity is a probability distribution of the unknown parameter, that produces data that aligns with…

机器学习 · 统计学 2024-10-02 Qin Li , Maria Oprea , Li Wang , Yunan Yang

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…

概率论 · 数学 2017-07-04 Jonathan Weed , Francis Bach

Diffusion models accomplish remarkable success in data generation tasks across various domains. However, the iterative sampling process is computationally expensive. Consistency models are proposed to learn consistency functions to map from…

机器学习 · 计算机科学 2025-05-07 Yiding Chen , Yiyi Zhang , Owen Oertell , Wen Sun

We consider the use of randomised forward models and log-likelihoods within the Bayesian approach to inverse problems. Such random approximations to the exact forward model or log-likelihood arise naturally when a computationally expensive…

统计理论 · 数学 2019-10-29 H. C. Lie , T. J. Sullivan , A. L. Teckentrup

Shape constraints yield flexible middle grounds between fully nonparametric and fully parametric approaches to modeling distributions of data. The specific assumption of log-concavity is motivated by applications across economics, survival…

统计方法学 · 统计学 2024-04-16 Robin Dunn , Aditya Gangrade , Larry Wasserman , Aaditya Ramdas
‹ 上一页 1 2 3 10 下一页 ›