English
Related papers

Related papers: Measure Transport with Kernel Stein Discrepancy

200 papers

Stein Variational Gradient Descent (SVGD), a popular sampling algorithm, is often described as the kernelized gradient flow for the Kullback-Leibler divergence in the geometry of optimal transport. We introduce a new perspective on SVGD…

Statistics Theory · Mathematics 2020-06-05 Sinho Chewi , Thibaut Le Gouic , Chen Lu , Tyler Maunu , Philippe Rigollet

Optimal transport has been very successful for various machine learning tasks; however, it is known to suffer from the curse of dimensionality. Hence, dimensionality reduction is desirable when applied to high-dimensional data with…

Machine Learning · Statistics 2025-07-21 Jie Wang , March Boedihardjo , Yao Xie

Kernel methods underpin many of the most successful approaches in data science and statistics, and they allow representing probability measures as elements of a reproducing kernel Hilbert space without loss of information. Recently, the…

Machine Learning · Statistics 2025-03-19 Florian Kalinke , Zoltan Szabo , Bharath K. Sriperumbudur

Distances between probability distributions are a key component of many statistical machine learning tasks, from two-sample testing to generative modeling, among others. We introduce a novel distance between measures that compares them…

Machine Learning · Statistics 2025-07-09 Arturo Castellanos , Anna Korba , Pavlo Mozharovskyi , Hicham Janati

We propose a dimension reduction technique for Bayesian inverse problems with nonlinear forward operators, non-Gaussian priors, and non-Gaussian observation noise. The likelihood function is approximated by a ridge function, i.e., a map…

Probability · Mathematics 2022-01-31 Olivier Zahm , Tiangang Cui , Kody Law , Alessio Spantini , Youssef Marzouk

The Kullback-Leibler divergence, the Kullback-Leibler variation, and the Bernstein "norm" are used to quantify discrepancies among probability distributions in likelihood models such as nonparametric maximum likelihood and nonparametric…

Statistics Theory · Mathematics 2026-01-27 Tetsuya Kaji

Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over…

Computation and Language · Computer Science 2024-12-10 Taiqiang Wu , Chaofan Tao , Jiahao Wang , Runming Yang , Zhe Zhao , Ngai Wong

A common way to quantify the ,,distance'' between measures is via their discrepancy, also known as maximum mean discrepancy (MMD). Discrepancies are related to Sinkhorn divergences $S_\varepsilon$ with appropriate cost functions as…

Optimization and Control · Mathematics 2020-08-25 Sebastian Neumayer , Gabriele Steidl

Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty quantification. In this paper, we develop a method for comparing how close different generative…

Machine Learning · Statistics 2025-10-24 Zijun Gao , Yan Sun , Han Su

Motivated by the computation of the non-parametric maximum likelihood estimator (NPMLE) and the Bayesian posterior in statistics, this paper explores the problem of convex optimization over the space of all probability distributions. We…

Statistics Theory · Mathematics 2023-11-03 Rentian Yao , Linjun Huang , Yun Yang

In this work, a novel sequential Monte Carlo filter is introduced which aims at efficient sampling of high-dimensional state spaces with a limited number of particles. Particles are pushed forward from the prior to the posterior density…

Machine Learning · Statistics 2018-05-30 Manuel Pulido , Peter Jan vanLeeuwen

We study the Kullback--Leibler (KL) divergence approximation theory of Gaussian mixture models (GMMs) by isolating an abstract mechanism behind several necessary-and-sufficient statements. The necessity direction is universal: if a density…

Statistics Theory · Mathematics 2026-04-14 Hien Duy Nguyen

Kullback-Leibler (KL) divergence is one of the most important divergence measures between probability distributions. In this paper, we prove several properties of KL divergence between multivariate Gaussian distributions. First, for any two…

Information Theory · Computer Science 2023-01-24 Yufeng Zhang , Wanwei Liu , Zhenbang Chen , Ji Wang , Kenli Li

Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-precision detection…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Xue Yang , Xiaojiang Yang , Jirui Yang , Qi Ming , Wentao Wang , Qi Tian , Junchi Yan

It was recently shown that under smoothness conditions, the squared Wasserstein distance between two distributions could be efficiently computed with appealing statistical error upper bounds. However, rather than the distance itself, the…

Machine Learning · Statistics 2021-12-30 Boris Muzellec , Adrien Vacher , Francis Bach , François-Xavier Vialard , Alessandro Rudi

Shape restriction, like monotonicity or convexity, imposed on a function of interest, such as a regression or density function, allows for its estimation without smoothness assumptions. The concept of $k$-monotonicity encompasses a family…

Statistics Theory · Mathematics 2023-06-09 Kang Wang , Subhashis Ghosal

We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries. Stein Variational Mirror Descent and Mirrored Stein Variational Gradient Descent minimize the Kullback-Leibler (KL)…

Machine Learning · Statistics 2022-04-26 Jiaxin Shi , Chang Liu , Lester Mackey

The contributions of the paper span theoretical and implementational results. First, we prove that Kd-trees can be extended to spaces in which the distance is measured with an arbitrary Bregman divergence. Perhaps surprisingly, this shows…

Computational Geometry · Computer Science 2025-02-20 Tuyen Pham , Hubert Wagner

This paper concerns the approximation of probability measures on $\mathbf{R}^d$ with respect to the Kullback-Leibler divergence. Given an admissible target measure, we show the existence of the best approximation, with respect to this…

Probability · Mathematics 2017-06-26 Yulong Lu , Andrew M. Stuart , Hendrik Weber

Recent work has attempted to directly approximate the `function-space' or predictive posterior distribution of Bayesian models, without approximating the posterior distribution over the parameters. This is appealing in e.g. Bayesian neural…

Machine Learning · Statistics 2020-11-19 David R. Burt , Sebastian W. Ober , Adrià Garriga-Alonso , Mark van der Wilk