English
Related papers

Related papers: Weighted quantization using MMD: From mean field t…

200 papers

Integration against a probability distribution given its unnormalized density is a central task in Bayesian inference and other fields. We introduce new methods for approximating such expectations with a small set of weighted samples --…

Machine Learning · Statistics 2026-05-15 Ayoub Belhadji , Daniel Sharp , Youssef M. Marzouk

We construct a Wasserstein gradient flow of the maximum mean discrepancy (MMD) and study its convergence properties. The MMD is an integral probability metric defined for a reproducing kernel Hilbert space (RKHS), and serves as a metric on…

Machine Learning · Statistics 2019-12-04 Michael Arbel , Anna Korba , Adil Salim , Arthur Gretton

Variational inference, such as the mean-field (MF) approximation, requires certain conjugacy structures for efficient computation. These can impose unnecessary restrictions on the viable prior distribution family and further constraints on…

Statistics Theory · Mathematics 2023-09-11 Rentian Yao , Yun Yang

We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distribution to target distribution with only target samples, either…

Many machine learning problems can be seen as approximating a \textit{target} distribution using a \textit{particle} distribution by minimizing their statistical discrepancy. Wasserstein Gradient Flow can move particles along a path that…

Machine Learning · Statistics 2024-06-07 Song Liu , Jiahao Yu , Jack Simons , Mingxuan Yi , Mark Beaumont

Many applications in machine learning involve data represented as probability distributions. The emergence of such data requires radically novel techniques to design tractable gradient flows on probability distributions over this type of…

Machine Learning · Computer Science 2025-06-10 Clément Bonet , Christophe Vauthier , Anna Korba

Accurate approximation of probability measures is essential in numerical applications. This paper explores the quantization of probability measures using the maximum mean discrepancy (MMD) distance as a guiding metric. We first investigate…

Optimization and Control · Mathematics 2025-03-18 Zahra Mehraban , Alois Pichler

Gradient flow in the 2-Wasserstein space is widely used to optimize functionals over probability distributions and is typically implemented using an interacting particle system with $n$ particles. Analyzing these algorithms requires showing…

Machine Learning · Computer Science 2026-03-27 Chandan Tankala , Dheeraj M. Nagaraj , Anant Raj

Mean shift is a simple interactive procedure that gradually shifts data points towards the mode which denotes the highest density of data points in the region. Mean shift algorithms have been effectively used for data denoising, mode…

Machine Learning · Computer Science 2021-05-11 Saptarshi Chakraborty , Debolina Paul , Swagatam Das

We propose a gradient flow procedure for generative modeling by transporting particles from an initial source distribution to a target distribution, where the gradient field on the particles is given by a noise-adaptive Wasserstein Gradient…

Machine Learning · Computer Science 2024-05-14 Alexandre Galashov , Valentin de Bortoli , Arthur Gretton

Several researchers have proposed minimisation of maximum mean discrepancy (MMD) as a method to quantise probability measures, i.e., to approximate a target distribution by a representative point set. We consider sequential algorithms that…

Machine Learning · Statistics 2021-02-15 Onur Teymur , Jackson Gorham , Marina Riabiz , Chris. J. Oates

Various machine learning tasks, from generative modeling to domain adaptation, revolve around the concept of dataset transformation and manipulation. While various methods exist for transforming unlabeled datasets, principled methods to do…

Machine Learning · Computer Science 2021-06-17 David Alvarez-Melis , Nicolò Fusi

This paper studies the optimization of the KL functional on the Wasserstein space of probability measures, and develops a sampling framework based on Wasserstein gradient descent (WGD). We identify two important subclasses of the…

Computation · Statistics 2026-02-04 Van Chien Ta , Thi Mai Hong Chu , Minh-Ngoc Tran

We propose conditional flows of the maximum mean discrepancy (MMD) with the negative distance kernel for posterior sampling and conditional generative modeling. This MMD, which is also known as energy distance, has several advantageous…

There has been recent interest in developing scalable Bayesian sampling methods such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD) for big-data analysis. A standard SG-MCMC algorithm simulates samples…

Machine Learning · Statistics 2018-07-11 Changyou Chen , Ruiyi Zhang , Wenlin Wang , Bai Li , Liqun Chen

Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-smooth Riesz kernels show a rich structure as singular measures can become absolutely continuous ones and conversely. In this paper we contribute to the…

Machine Learning · Computer Science 2024-03-22 Fabian Altekrüger , Johannes Hertrich , Gabriele Steidl

Wasserstein gradient flows are continuous time dynamics that define curves of steepest descent to minimize an objective function over the space of probability measures (i.e., the Wasserstein space). This objective is typically a divergence…

Optimization and Control · Mathematics 2021-02-23 Adil Salim , Anna Korba , Giulia Luise

The maximum mean discrepancy and Wasserstein distance are popular distance measures between distributions and play important roles in many machine learning problems such as metric learning, generative modeling, domain adaption, and…

Machine Learning · Computer Science 2025-01-22 Dong Qiao , Jicong Fan

In Bayesian inference, the posterior distributions are difficult to obtain analytically for complex models such as neural networks. Variational inference usually uses a parametric distribution for approximation, from which we can easily…

Machine Learning · Statistics 2019-02-01 Futoshi Futami , Zhenghang Cui , Issei Sato , Masashi Sugiyama

Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not scalable as they assume access to the complete set of…

Machine Learning · Statistics 2026-03-10 Eduardo Fernandes Montesuma , Yassir Bendou , Mike Gartrell
‹ Prev 1 2 3 10 Next ›