中文
相关论文

相关论文: Advancing Wasserstein Convergence Analysis of Scor…

200 篇论文

We propose a new minimum-distance estimator for linear random coefficient models. This estimator integrates the recently advanced sliced Wasserstein distance with the nearest neighbor methods, both of which enhance computational efficiency.…

统计理论 · 数学 2025-04-25 Keunwoo Lim , Ting Ye , Fang Han

This paper explores the use of score-based diffusion models for Bayesian image reconstruction. Diffusion models are an efficient tool for generative modeling. Diffusion models can also be used for solving image reconstruction problems. We…

图像与视频处理 · 电气工程与系统科学 2025-10-06 Michael T. McCann , Hyungjin Chung , Jong Chul Ye , Marc L. Klasky

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…

最优化与控制 · 数学 2026-05-28 Tam Le

We consider sampling from a Gibbs distribution by evolving a finite number of particles using a particular score estimator rather than Brownian motion. To accelerate the particles, we consider a second-order score-based ODE, similar to…

机器学习 · 统计学 2026-01-19 Hong Ye Tan , Stanley Osher , Wuchen Li

Diffusion models for continuous state spaces based on Gaussian noising processes are now relatively well understood from both practical and theoretical perspectives. In contrast, results for diffusion models on discrete state spaces remain…

机器学习 · 计算机科学 2026-04-02 Giovanni Conforti , Alain Durmus , Le-Tuyet-Nhi Pham , Gael Raoul

Score-based models have achieved remarkable results in the generative modeling of many domains. By learning the gradient of smoothed data distribution, they can iteratively generate samples from complex distribution e.g. natural images.…

人工智能 · 计算机科学 2024-03-27 Binxu Wang , John J. Vastola

Diffusion probabilistic models generate samples by learning to reverse a noise-injection process that transforms data into noise. A key development is the reformulation of the reverse sampling process as a deterministic probability flow…

机器学习 · 计算机科学 2025-08-15 Daniel Zhengyu Huang , Jiaoyang Huang , Zhengjiang Lin

By learning the gradient of smoothed data distributions, diffusion models can iteratively generate samples from complex distributions. The learned score function enables their generalization capabilities, but how the learned score relates…

机器学习 · 计算机科学 2024-12-16 Binxu Wang , John J. Vastola

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…

机器学习 · 统计学 2023-10-03 Hong Ye Tan , Stanley Osher , Wuchen Li

Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by high sampling costs. While prior work focuses on training objectives or individual solvers,…

机器学习 · 计算机科学 2026-02-16 Sangwoo Jo , Sungjoon Choi

We develop a Bayesian inference method for diffusions observed discretely and with noise, which is free of discretisation bias. Unlike existing unbiased inference methods, our method does not rely on exact simulation techniques. Instead,…

统计方法学 · 统计学 2021-03-10 Neil K. Chada , Jordan Franks , Ajay Jasra , Kody J. H. Law , Matti Vihola

Ranking distributions according to a stochastic order has wide applications in diverse areas. Although stochastic dominance has received much attention, convex order, particularly in general dimensions, has yet to be investigated from a…

统计方法学 · 统计学 2025-01-15 Jakwang Kim , Young-Heon Kim , Yuanlong Ruan , Andrew Warren

We present a way to use Stein's method in order to bound the Wasserstein distance of order $2$ between two measures $\nu$ and $\mu$ supported on $\mathbb{R}^d$ such that $\mu$ is the reversible measure of a diffusion process. In order to…

概率论 · 数学 2018-06-25 Thomas Bonis

Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling, due to their state-of-the art performance in many generation tasks while relying on mathematical foundations such as stochastic…

机器学习 · 计算机科学 2023-11-28 Teo Deveney , Jan Stanczuk , Lisa Maria Kreusser , Chris Budd , Carola-Bibiane Schönlieb

Score Distillation Sampling (SDS) has been pivotal for leveraging pre-trained diffusion models in downstream tasks such as inverse problems, but it faces two major challenges: $(i)$ mode collapse and $(ii)$ latent space inversion, which…

机器学习 · 计算机科学 2024-10-15 Nicolas Zilberstein , Morteza Mardani , Santiago Segarra

Many normalizing flow architectures impose regularity constraints, yet their distributional approximation properties are not fully characterized. We study the expressivity of bi-Lipschitz normalizing flows through the lens of score-based…

机器学习 · 统计学 2026-05-08 Meira Iske , Carola-Bibiane Schönlieb

Score-based diffusion models are a recently developed framework for posterior sampling in Bayesian inverse problems with a state-of-the-art performance for severely ill-posed problems by leveraging a powerful prior distribution learned from…

Recent advances in diffusion models bring state-of-the-art performance on image generation tasks. However, empirical results from previous research in diffusion models imply an inverse correlation between density estimation and sample…

机器学习 · 计算机科学 2022-06-14 Dongjun Kim , Seungjae Shin , Kyungwoo Song , Wanmo Kang , Il-Chul Moon

Score-based diffusion models are a highly effective method for generating samples from a distribution of images. We consider scenarios where the training data comes from a noisy version of the target distribution, and present an efficiently…

机器学习 · 统计学 2025-09-30 Dennis Elbrächter , Giovanni S. Alberti , Matteo Santacesaria

Score-based Generative Models (SGMs) aim to sample from a target distribution by learning score functions using samples perturbed by Gaussian noise. Existing convergence bounds for SGMs in the W2-distance rely on stringent assumptions about…

机器学习 · 统计学 2025-12-12 Marta Gentiloni-Silveri , Antonio Ocello