中文
相关论文

相关论文: A Unified Framework for Data-Free One-Step Samplin…

200 篇论文

The Wasserstein-Fisher-Rao (WFR) metric extends dynamic optimal transport (OT) by coupling displacement with change of mass, providing a principled geometry for modeling unbalanced snapshot dynamics. Existing WFR solvers, however, are often…

机器学习 · 计算机科学 2026-04-03 Qiangwei Peng , Zihan Wang , Junda Ying , Yuhao Sun , Qing Nie , Lei Zhang , Tiejun Li , Peijie Zhou

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic…

统计理论 · 数学 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

最优化与控制 · 数学 2018-10-30 Lenaic Chizat , Francis Bach

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…

统计计算 · 统计学 2026-02-04 Van Chien Ta , Thi Mai Hong Chu , Minh-Ngoc Tran

The conventional understanding of adversarial training in generative adversarial networks (GANs) is that the discriminator is trained to estimate a divergence, and the generator learns to minimize this divergence. We argue that despite the…

机器学习 · 统计学 2023-08-09 Mingxuan Yi , Zhanxing Zhu , Song Liu

Score-based diffusion models currently constitute the state of the art in continuous generative modeling. These methods are typically formulated via overdamped or underdamped Ornstein--Uhlenbeck-type stochastic differential equations, in…

机器学习 · 计算机科学 2025-12-22 Herlock Rahimi

Diffusion models are commonly interpreted as learning the score function, i.e., the gradient of the log-density of noisy data. However, this assumption implies that the target of learning is a conservative vector field, which is not…

机器学习 · 计算机科学 2025-09-03 An B. Vuong , Michael T. McCann , Javier E. Santos , Yen Ting Lin

We propose the characteristic generator, a novel one-step generative model that combines the efficiency of sampling in Generative Adversarial Networks (GANs) with the stable performance of flow-based models. Our model is driven by…

机器学习 · 计算机科学 2025-12-29 Zhao Ding , Chenguang Duan , Yuling Jiao , Ruoxuan Li , Jerry Zhijian Yang , Pingwen Zhang

We propose \emph{Euler Mean Flows (EMF)}, a flow-based generative framework for one-step and few-step generation that enforces long-range trajectory consistency with minimal sampling cost. The key idea of EMF is to replace the trajectory…

机器学习 · 计算机科学 2026-02-04 Zhiqi Li , Yuchen Sun , Duowen Chen , Jinjin He , Bo Zhu

Sampling from diffusion models involves a slow iterative process that hinders their practical deployment, especially for interactive applications. To accelerate generation speed, recent approaches distill a multi-step diffusion model into a…

机器学习 · 计算机科学 2025-03-11 Yilun Xu , Weili Nie , Arash Vahdat

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Chaoyang Wang , Yunhai Tong

Statistical surrogate modeling of fluid flows is hard because dynamics are multiscale and highly sensitive to initial conditions. Conditional diffusion surrogates can be accurate, but usually need hundreds of stochastic sampling steps. We…

机器学习 · 计算机科学 2026-02-10 Victor Armegioiu , Yannick Ramic , Siddhartha Mishra

We present a framework enabling variational data assimilation for gradient flows in general metric spaces, based on the minimizing movement (or Jordan-Kinderlehrer-Otto) approximation scheme. After discussing stability properties in the…

数值分析 · 数学 2023-01-18 Jan-F. Pietschmann , Matthias Schlottbom

Particle-based variational inference methods (ParVIs) such as Stein variational gradient descent (SVGD) update the particles based on the kernelized Wasserstein gradient flow for the Kullback-Leibler (KL) divergence. However, the design of…

机器学习 · 统计学 2023-10-26 Ziheng Cheng , Shiyue Zhang , Longlin Yu , Cheng Zhang

Existing machine learning literature lacks graph-based domain adaptation techniques capable of handling large distribution shifts, primarily due to the difficulty in simulating a coherent evolutionary path from source to target graph. To…

机器学习 · 计算机科学 2026-05-14 Pui Ieng Lei , Ximing Chen , Yijun Sheng , Yanyan Liu , Zhiguo Gong , Qiang Yang

We study a system of drift-diffusion PDEs for a potentially infinite number of incompressible phases, subject to a joint pointwise volume constraint. Our analysis is based on the interpretation as a collection of coupled Wasserstein…

偏微分方程分析 · 数学 2024-11-22 Clément Cancès , Daniel Matthes , Ismael Medina , Bernhard Schmitzer

Flow Matching, a promising approach in generative modeling, has recently gained popularity. Relying on ordinary differential equations, it offers a simple and flexible alternative to diffusion models, which are currently the…

机器学习 · 统计学 2026-03-13 Lea Kunkel

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…

机器学习 · 计算机科学 2021-06-17 David Alvarez-Melis , Nicolò Fusi

Safety assurance is uncompromisable for safety-critical environments with the presence of drastic model uncertainties (e.g., distributional shift), especially with humans in the loop. However, incorporating uncertainty in safe learning will…

机器学习 · 计算机科学 2023-10-05 Alaa Eddine Chriat , Chuangchuang Sun

Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood. This paper rigorously analyzes the convergence properties of gradient flow in…

机器学习 · 统计学 2024-11-01 Cheng Gao , Yuan Cao , Zihao Li , Yihan He , Mengdi Wang , Han Liu , Jason Matthew Klusowski , Jianqing Fan