English
Related papers

Related papers: Score-based Generative Modeling Secretly Minimizes…

200 papers

Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the…

Machine Learning · Statistics 2019-08-23 Leon Bottou , Martin Arjovsky , David Lopez-Paz , Maxime Oquab

Diffusion models are a new class of generative models that revolve around the estimation of the score function associated with a stochastic differential equation. Subsequent to its acquisition, the approximated score function is then…

Statistics Theory · Mathematics 2024-09-13 Giovanni Conforti , Alain Durmus , Marta Gentiloni Silveri

This paper considers the problem of regression over distributions, which is becoming increasingly important in machine learning. Existing approaches often ignore the geometry of the probability space or are computationally expensive. To…

Machine Learning · Computer Science 2025-10-31 Maksim Maslov , Alexander Kugaevskikh , Matthew Ivanov

Generative modeling aims to produce new random examples from an unknown target distribution, given access to a finite collection of examples. Among the leading approaches, denoising diffusion probabilistic models (DDPMs) construct such…

Machine Learning · Statistics 2025-06-12 Vahan Arsenyan , Elen Vardanyan , Arnak Dalalyan

Generative Adversarial Networks (GANs) are one of the most practical methods for learning data distributions. A popular GAN formulation is based on the use of Wasserstein distance as a metric between probability distributions.…

Machine Learning · Computer Science 2018-05-23 Maziar Sanjabi , Jimmy Ba , Meisam Razaviyayn , Jason D. Lee

Optimal transport is widely used to learn distributions, enforce distributional constraints, and model uncertainty. In applications, transport losses are often computed from samples through tractable representations, such as one-dimensional…

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

Score-based diffusion models have emerged as powerful tools in generative modeling, yet their theoretical foundations remain underexplored. In this work, we focus on the Wasserstein convergence analysis of score-based diffusion models.…

Machine Learning · Statistics 2025-02-10 Yifeng Yu , Lu Yu

Minimum expected distance estimation (MEDE) algorithms have been widely used for probabilistic models with intractable likelihood functions and they have become increasingly popular due to their use in implicit generative modeling (e.g.…

Machine Learning · Statistics 2020-03-25 Kimia Nadjahi , Alain Durmus , Umut Şimşekli , Roland Badeau

We study the efficacy and efficiency of deep generative networks for approximating probability distributions. We prove that neural networks can transform a low-dimensional source distribution to a distribution that is arbitrarily close to a…

Machine Learning · Computer Science 2023-12-05 Yunfei Yang , Zhen Li , Yang Wang

In this paper, we investigate the properties of the Sliced Wasserstein Distance (SW) when employed as an objective functional. The SW metric has gained significant interest in the optimal transport and machine learning literature, due to…

Machine Learning · Statistics 2025-08-21 Christophe Vauthier , Anna Korba , Quentin Mérigot

The Wasserstein distance is a distance between two probability distributions and has recently gained increasing popularity in statistics and machine learning, owing to its attractive properties. One important approach to extending this…

Methodology · Statistics 2022-02-14 Ryo Okano , Masaaki Imaizumi

Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets. GANs are notoriuos for training difficulties and their dependence on arbitrary hyperparameters. One recent…

Machine Learning · Computer Science 2019-10-03 Thomas Pinetz , Daniel Soukup , Thomas Pock

Sliced-Wasserstein distance (SW) and its variant, Max Sliced-Wasserstein distance (Max-SW), have been used widely in the recent years due to their fast computation and scalability even when the probability measures lie in a very high…

Machine Learning · Statistics 2020-10-06 Khai Nguyen , Nhat Ho , Tung Pham , Hung Bui

The mathematical forces at work behind Generative Adversarial Networks raise challenging theoretical issues. Motivated by the important question of characterizing the geometrical properties of the generated distributions, we provide a…

Machine Learning · Statistics 2023-10-06 Arthur Stéphanovitch , Ugo Tanielian , Benoît Cadre , Nicolas Klutchnikoff , Gérard Biau

We propose a deterministic sampling framework using Score-Based Transport Modeling for sampling an unnormalized target density $\pi$ given only its score $\nabla \log \pi$. Our method approximates the Wasserstein gradient flow on…

Machine Learning · Computer Science 2025-10-21 Vasily Ilin , Peter Sushko , Jingwei Hu

We focus on the fundamental mathematical structure of score-based generative models (SGMs). We first formulate SGMs in terms of the Wasserstein proximal operator (WPO) and demonstrate that, via mean-field games (MFGs), the WPO formulation…

Machine Learning · Statistics 2024-02-12 Benjamin J. Zhang , Siting Liu , Wuchen Li , Markos A. Katsoulakis , Stanley J. Osher

Generating samples given a specific label requires estimating conditional distributions. We derive a tractable upper bound of the Wasserstein distance between conditional distributions to lay the theoretical groundwork to learn conditional…

Machine Learning · Statistics 2023-08-29 Young-geun Kim , Kyungbok Lee , Youngwon Choi , Joong-Ho Won , Myunghee Cho Paik

Wasserstein GANs are based on the idea of minimising the Wasserstein distance between a real and a generated distribution. We provide an in-depth mathematical analysis of differences between the theoretical setup and the reality of training…

Machine Learning · Statistics 2021-10-06 Jan Stanczuk , Christian Etmann , Lisa Maria Kreusser , Carola-Bibiane Schönlieb

Generative adversarial nets (GANs) and variational auto-encoders have significantly improved our distribution modeling capabilities, showing promise for dataset augmentation, image-to-image translation and feature learning. However, to…

Denoising diffusion models are a recent class of generative models exhibiting state-of-the-art performance in image and audio synthesis. Such models approximate the time-reversal of a forward noising process from a target distribution to a…

Machine Learning · Statistics 2023-05-30 Valentin De Bortoli