English
Related papers

Related papers: Geometry-Aware Langevin Sampling for Matrix-Valued…

200 papers

The Metropolis-adjusted Langevin (MALA) algorithm is a sampling algorithm which makes local moves by incorporating information about the gradient of the logarithm of the target density. In this paper we study the efficiency of MALA on a…

Probability · Mathematics 2012-11-29 Natesh S. Pillai , Andrew M. Stuart , Alexandre H. Thiéry

Given i.i.d. observations of a random vector $X \in \mathbb{R}^p$, we study the problem of estimating both its covariance matrix $\Sigma^*$, and its inverse covariance or concentration matrix {$\Theta^* = (\Sigma^*)^{-1}$.} We estimate…

Machine Learning · Statistics 2008-11-24 Pradeep Ravikumar , Martin J. Wainwright , Garvesh Raskutti , Bin Yu

We consider the problem of efficiently approximating and encoding high-dimensional data sampled from a probability distribution $\rho$ in $\mathbb{R}^D$, that is nearly supported on a $d$-dimensional set $\mathcal{M}$ - for example…

Machine Learning · Statistics 2017-07-19 Wenjing Liao , Mauro Maggioni

We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics. The proposed algorithm is essentially a…

Machine Learning · Statistics 2022-05-24 Wei Deng , Guang Lin , Faming Liang

Differential geometric approaches to the analysis and processing of data in the form of symmetric positive definite (SPD) matrices have had notable successful applications to numerous fields including computer vision, medical imaging, and…

Differential Geometry · Mathematics 2024-06-10 Cyrus Mostajeran , Nathaël Da Costa , Graham Van Goffrier , Rodolphe Sepulchre

While the Metropolis Adjusted Langevin Algorithm (MALA) is a popular and widely used Markov chain Monte Carlo method, very few papers derive conditions that ensure its convergence. In particular, to the authors' knowledge, assumptions that…

Computation · Statistics 2022-01-07 Alain Durmus , Éric Moulines

Geometric variations like rotation, scaling, and viewpoint changes pose a significant challenge to visual understanding. One common solution is to directly model certain intrinsic structures, e.g., using landmarks. However, it then becomes…

Machine Learning · Statistics 2020-10-13 Xiuyuan Cheng , Zichen Miao , Qiang Qiu

Understanding the dimension dependency of computational complexity in high-dimensional sampling problem is a fundamental problem, both from a practical and theoretical perspective. Compared with samplers with unbiased stationary…

Machine Learning · Computer Science 2024-03-12 Xunpeng Huang , Hanze Dong , Difan Zou , Tong Zhang

We define an optimal preconditioning for the Langevin diffusion by analytically optimizing the expected squared jumped distance. This yields as the optimal preconditioning an inverse Fisher information covariance matrix, where the…

Machine Learning · Statistics 2023-10-31 Michalis K. Titsias

We present a new class of Langevin based algorithms, which overcomes many of the known shortcomings of popular adaptive optimizers that are currently used for the fine tuning of deep learning models. Its underpinning theory relies on recent…

Machine Learning · Computer Science 2024-03-05 Dong-Young Lim , Sotirios Sabanis

This paper presents a new accelerated proximal Markov chain Monte Carlo methodology to perform Bayesian inference in imaging inverse problems with an underlying convex geometry. The proposed strategy takes the form of a stochastic relaxed…

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

Signed graphs are equipped with both positive and negative edge weights, encoding pairwise correlations as well as anti-correlations in data. A balanced signed graph has no cycles of odd number of negative edges. Laplacian of a balanced…

Machine Learning · Computer Science 2024-09-13 Haruki Yokota , Hiroshi Higashi , Yuichi Tanaka , Gene Cheung

We utilise a sampler originating from nonequilibrium statistical mechanics, termed here Jarzynski-adjusted Langevin algorithm (JALA), to build statistical estimation methods in latent variable models. We achieve this by leveraging…

Computation · Statistics 2025-10-27 James Cuin , Davide Carbone , O. Deniz Akyildiz

Hyperparameter tuning is one of the essential steps to guarantee the convergence of machine learning models. We argue that intuition about the optimal choice of hyperparameters for stochastic gradient descent can be obtained by studying a…

Disordered Systems and Neural Networks · Physics 2025-12-12 Chanju Park , Biagio Lucini , Gert Aarts

Laplacian regularized stratified models (LRSM) are models that utilize the explicit or implicit network structure of the sub-problems as defined by the categorical features called strata (e.g., age, region, time, forecast horizon, etc.),…

Machine Learning · Statistics 2023-05-05 Ziheng Cheng , Junzi Zhang , Akshay Agrawal , Stephen Boyd

Graphs serve as generic tools to encode the underlying relational structure of data. Often this graph is not given, and so the task of inferring it from nodal observations becomes important. Traditional approaches formulate a convex inverse…

Machine Learning · Computer Science 2024-06-24 Max Wasserman , Gonzalo Mateos

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

Low-dimensional structure in real-world data plays an important role in the success of generative models, which motivates diffusion models defined on intrinsic data manifolds. Such models are driven by stochastic differential equations…

Machine Learning · Statistics 2026-03-05 Zhiyuan Zhan , Masashi Sugiyama

Representations in the form of Symmetric Positive Definite (SPD) matrices have been popularized in a variety of visual learning applications due to their demonstrated ability to capture rich second-order statistics of visual data. There…