English
Related papers

Related papers: Sliced Wasserstein Generative Models

200 papers

Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a…

Optimization and Control · Mathematics 2026-05-28 Tam Le

Collections of probability distributions arise in a variety of applications ranging from user activity pattern analysis to brain connectomics. In practice these distributions can be defined over diverse domain types including finite…

Methodology · Statistics 2023-06-16 Raif Rustamov , Subhabrata Majumdar

Recently, Deng et al. (2026) proposed Generative Modeling via Drifting (GMD), a novel framework for generative tasks. This note presents an analysis of GMD through the lens of Wasserstein Gradient Flows (WGF), i.e., the path of steepest…

Machine Learning · Computer Science 2026-05-22 Arthur Gretton , Li Kevin Wenliang , Alexandre Galashov , James Thornton , Valentin De Bortoli , Arnaud Doucet

Personalized recommender systems are playing an increasingly important role as more content and services become available and users struggle to identify what might interest them. Although matrix factorization and deep learning based methods…

Information Retrieval · Computer Science 2021-01-14 Chen Ma , Liheng Ma , Yingxue Zhang , Ruiming Tang , Xue Liu , Mark Coates

Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning. In this work, we accelerate SGD by adaptively learning how to sample the most useful training examples at each time…

Machine Learning · Computer Science 2016-03-16 Guillaume Bouchard , Théo Trouillon , Julien Perez , Adrien Gaidon

An increasing number of machine learning tasks deal with learning representations from set-structured data. Solutions to these problems involve the composition of permutation-equivariant modules (e.g., self-attention, or individual…

Machine Learning · Computer Science 2021-03-09 Navid Naderializadeh , Soheil Kolouri , Joseph F. Comer , Reed W. Andrews , Heiko Hoffmann

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models. However, further reducing the number of sampling steps…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Nikita Starodubcev , Ilya Drobyshevskiy , Denis Kuznedelev , Artem Babenko , Dmitry Baranchuk

This paper uses sample data to study the problem of comparing populations on finite-dimensional parallelizable Riemannian manifolds and more general trivial vector bundles. Utilizing triviality, our framework represents populations as…

Methodology · Statistics 2023-11-29 Michael Wilson , Tom Needham , Chiwoo Park , Suprateek Kundu , Anuj Srivastava

Detecting tiny objects is a very challenging problem since a tiny object only contains a few pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory results on tiny objects due to the lack of appearance…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Jinwang Wang , Chang Xu , Wen Yang , Lei Yu

Distance measures between graphs are important primitives for a variety of learning tasks. In this work, we describe an unsupervised, optimal transport based approach to define a distance between graphs. Our idea is to derive…

Computational Engineering, Finance, and Science · Computer Science 2024-04-11 Michael Scholkemper , Damin Kühn , Gerion Nabbefeld , Simon Musall , Björn Kampa , Michael T. Schaub

In this work, we introduce a novel framework for privately optimizing objectives that rely on Wasserstein distances between data-dependent empirical measures. Our main theoretical contribution is, based on an explicit formulation of the…

Machine Learning · Computer Science 2025-05-22 David Rodríguez-Vítores , Clément Lalanne , Jean-Michel Loubes

Generative modeling typically concerns transporting a single source distribution to a target distribution via simple probability flows. However, in fields like computer graphics and single-cell genomics, samples themselves can be viewed as…

Machine Learning · Computer Science 2025-05-20 Doron Haviv , Aram-Alexandre Pooladian , Dana Pe'er , Brandon Amos

Generative adversarial networks (GANs) have received a tremendous amount of attention in the past few years, and have inspired applications addressing a wide range of problems. Despite its great potential, GANs are difficult to train.…

Machine Learning · Computer Science 2017-05-09 Zhimin Chen , Yuguang Tong

Score-based generative models (SGMs) is a recent class of deep generative models with state-of-the-art performance in many applications. In this paper, we establish convergence guarantees for a general class of SGMs in 2-Wasserstein…

Machine Learning · Computer Science 2025-02-18 Xuefeng Gao , Hoang M. Nguyen , Lingjiong Zhu

Dataset Distillation (DD) aims to generate a compact synthetic dataset that enables models to achieve performance comparable to training on the full large dataset, significantly reducing computational costs. Drawing from optimal transport…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Haoyang Liu , Yijiang Li , Tiancheng Xing , Peiran Wang , Vibhu Dalal , Luwei Li , Jingrui He , Haohan Wang

Distance weighted discrimination (DWD) is a linear discrimination method that is particularly well-suited for classification tasks with high-dimensional data. The DWD coefficients minimize an intuitive objective function, which can solved…

Methodology · Statistics 2020-10-08 Eric F. Lock

Gaussian mixture models (GMM) are powerful parametric tools with many applications in machine learning and computer vision. Expectation maximization (EM) is the most popular algorithm for estimating the GMM parameters. However, EM…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Soheil Kolouri , Gustavo K. Rohde , Heiko Hoffmann

When dealing with electro or magnetoencephalography records, many supervised prediction tasks are solved by working with covariance matrices to summarize the signals. Learning with these matrices requires using Riemanian geometry to account…

We develop a kernel projected Wasserstein distance for the two-sample test, an essential building block in statistics and machine learning: given two sets of samples, to determine whether they are from the same distribution. This method…

Statistics Theory · Mathematics 2022-05-10 Jie Wang , Rui Gao , Yao Xie

Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown that it provides performances similar to its non-smoothed…

Machine Learning · Computer Science 2024-04-26 Mokhtar Z. Alaya , Alain Rakotomamonjy , Maxime Berar , Gilles Gasso