English
Related papers

Related papers: Adaptive step size selection for Hessian-based man…

200 papers

We study the mixing time of the Metropolis-adjusted Langevin algorithm (MALA) for sampling from a log-smooth and strongly log-concave distribution. We establish its optimal minimax mixing time under a warm start. Our main contribution is…

Machine Learning · Statistics 2022-10-04 Keru Wu , Scott Schmidler , Yuansi Chen

Stochastic gradients have been widely integrated into Langevin-based methods to improve their scalability and efficiency in solving large-scale sampling problems. However, the proximal sampler, which exhibits much faster convergence than…

Machine Learning · Statistics 2024-05-28 Xunpeng Huang , Difan Zou , Yi-An Ma , Hanze Dong , Tong Zhang

Proposals for Metropolis-Hastings MCMC derived by discretizing Langevin diffusion or Hamiltonian dynamics are examples of stochastic autoregressive proposals that form a natural wider class of proposals with equivalent computability. We…

Computation · Statistics 2016-10-05 Richard A. Norton , Colin Fox

We propose a new sampling algorithm combining two quite powerful ideas in the Markov chain Monte Carlo literature -- adaptive Metropolis sampler and two-stage Metropolis-Hastings sampler. The proposed sampling method will be particularly…

Computation · Statistics 2021-01-05 Anirban Mondal , Kai Yin , Abhijit Mandal

A simple and efficient adaptive Markov Chain Monte Carlo (MCMC) method, called the Metropolized Adaptive Subspace (MAdaSub) algorithm, is proposed for sampling from high-dimensional posterior model distributions in Bayesian variable…

Methodology · Statistics 2023-01-04 Christian Staerk , Maria Kateri , Ioannis Ntzoufras

We consider the problem of sampling from a distribution governed by a potential function. This work proposes an explicit score based MCMC method that is deterministic, resulting in a deterministic evolution for particles rather than a…

Machine Learning · Statistics 2023-10-03 Hong Ye Tan , Stanley Osher , Wuchen Li

We consider the Random Walk Metropolis algorithm on $\mathbb{R}^n$ with Gaussian proposals, and when the target probability measure is the $n$-fold product of a one-dimensional law. It is well known (see Roberts et al. (Ann. Appl. Probab. 7…

Methodology · Statistics 2014-10-22 Benjamin Jourdain , Tony Lelièvre , Błażej Miasojedow

Real-world data distributions are often highly skewed. This has spurred a growing body of research on long-tailed recognition, aimed at addressing the imbalance in training classification models. Among the methods studied, multiplicative…

Machine Learning · Computer Science 2025-03-11 Naoya Hasegawa , Issei Sato

For sufficiently smooth targets of product form it is known that the variance of a single coordinate of the proposal in RWM (Random walk Metropolis) and MALA (Metropolis adjusted Langevin algorithm) should optimally scale as $n^{-1}$ and as…

Probability · Mathematics 2020-07-15 Jure Vogrinc , Wilfrid Stephen Kendall

Conventional wisdom in the sampling literature, backed by a popular diffusion scaling limit, suggests that the mixing time of the Metropolis-Adjusted Langevin Algorithm (MALA) scales as $O(d^{1/3})$, where $d$ is the dimension. However, the…

Statistics Theory · Mathematics 2020-12-24 Sinho Chewi , Chen Lu , Kwangjun Ahn , Xiang Cheng , Thibaut Le Gouic , Philippe Rigollet

This work proposes a novel adaptive linearized alternating direction multiplier method (LADMM) to convex optimization, which improves the convergence rate of the LADMM-based algorithm by adjusting step-size iteratively.The innovation of…

Optimization and Control · Mathematics 2024-07-04 Boran Wang

Sequential optimization methods are often confronted with the curse of dimensionality in high-dimensional spaces. Current approaches under the Gaussian process framework are still burdened by the computational complexity of tracking…

Machine Learning · Computer Science 2024-01-08 Zeji Yi , Yunyue Wei , Chu Xin Cheng , Kaibo He , Yanan Sui

A natural method for the introduction of second-order derivatives of the log likelihood into MCMC algorithms is introduced, based on Taylor expansion of the Langevin equation followed by exact solution of the truncated system.

Computation · Statistics 2015-07-24 Thomas House

We present a two-stage Metropolis-Hastings algorithm for sampling probabilistic models, whose log-likelihood is computationally expensive to evaluate, by using a surrogate Gaussian Process (GP) model. The key feature of the approach, and…

Machine Learning · Statistics 2021-09-29 Alessio Benavoli , Jason Wyse , Arthur White

Piecewise-Deterministic Markov Processes (PDMPs) hold significant promise for sampling from complex probability distributions. However, their practical implementation is hindered by the need to compute model-specific bounds. Conversely,…

Computation · Statistics 2025-03-17 Augustin Chevallier , Sam Power , Matthew Sutton

Stochastic gradient Markov Chain Monte Carlo algorithms are popular samplers for approximate inference, but they are generally biased. We show that many recent versions of these methods (e.g. Chen et al. (2014)) cannot be corrected using…

Machine Learning · Statistics 2021-02-03 Adrià Garriga-Alonso , Vincent Fortuin

Markov chain Monte Carlo (MCMC), such as Langevin dynamics, is valid for approximating intractable distributions. However, its usage is limited in the context of deep latent variable models owing to costly datapoint-wise sampling iterations…

Machine Learning · Computer Science 2022-10-12 Shohei Taniguchi , Yusuke Iwasawa , Wataru Kumagai , Yutaka Matsuo

Manifold Markov chain Monte Carlo algorithms have been introduced to sample more effectively from challenging target densities exhibiting multiple modes or strong correlations. Such algorithms exploit the local geometry of the parameter…

Machine Learning · Statistics 2021-05-11 Theodore Papamarkou , Alexey Lindo , Eric B. Ford

Federated learning performed by a decentralized networks of agents is becoming increasingly important with the prevalence of embedded software on autonomous devices. Bayesian approaches to learning benefit from offering more information as…

Machine Learning · Computer Science 2021-07-16 Vyacheslav Kungurtsev , Adam Cobb , Tara Javidi , Brian Jalaian

The Linear Ballistic Accumulator (Brown & Heathcote, 2008) model is used as a measurement tool to answer questions about applied psychology. The analyses based on this model depend upon the model selected and its estimated parameters.…

Methodology · Statistics 2020-03-03 David Gunawan , Guy E. Hawkins , Minh-Ngoc Tran , Robert Kohn , Scott Brown