中文
相关论文

相关论文: Independent projections of diffusions: Gradient fl…

200 篇论文

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…

机器学习 · 计算机科学 2026-03-27 Chandan Tankala , Dheeraj M. Nagaraj , Anant Raj

We revisit the variational characterization of diffusion as entropic gradient flux and provide for it a probabilistic interpretation based on stochastic calculus. It was shown by Jordan, Kinderlehrer, and Otto that, for diffusions of…

概率论 · 数学 2020-03-24 Ioannis Karatzas , Walter Schachermayer , Bertram Tschiderer

Existing deterministic variational inference approaches for diffusion processes use simple proposals and target the marginal density of the posterior. We construct the variational process as a controlled version of the prior process and…

机器学习 · 计算机科学 2021-03-02 Christian Wildner , Heinz Koeppl

We formulate a class of velocity-free finite-particle methods for mass transport problems based on a time-discrete incremental variational principle that combines entropy and the cost of particle transport, as measured by the Wasserstein…

计算物理 · 物理学 2023-05-10 Anna Pandolfi , Laurent Stainier , Michael Ortiz

The Poisson-Nernst-Planck system of equations used to model ionic transport is interpreted as a gradient flow for the Wasserstein distance and a free energy in the space of probability measures with finite second moment. A variational…

偏微分方程分析 · 数学 2015-09-08 David Kinderlehrer , Léonard Monsaingeon , Xiang Xu

We introduce a novel discretization scheme for Wasserstein gradient flows that involves successively computing Schr\"{o}dinger bridges with the same marginals. This is different from both the forward/geodesic approximation and the…

概率论 · 数学 2024-06-18 Medha Agarwal , Zaid Harchaoui , Garrett Mulcahy , Soumik Pal

This paper contains two contributions in the study of optimal transport on metric graphs. Firstly, we prove a Benamou-Brenier formula for the Wasserstein distance, which establishes the equivalence of static and dynamical optimal transport.…

偏微分方程分析 · 数学 2022-05-02 Matthias Erbar , Dominik Forkert , Jan Maas , Delio Mugnolo

Diffusion-based models on continuous spaces have seen substantial recent progress through the mathematical framework of gradient flows, leveraging the Wasserstein-2 (${W}_2$) metric via the Jordan-Kinderlehrer-Otto (JKO) scheme. Despite the…

机器学习 · 计算机科学 2026-04-14 Dario Rancati , Jan Maas , Francesco Locatello

This paper introduces Wasserstein variational inference, a new form of approximate Bayesian inference based on optimal transport theory. Wasserstein variational inference uses a new family of divergences that includes both f-divergences and…

Flow Matching has recently gained attention in generative modeling as a simple and flexible alternative to diffusion models. While existing statistical guarantees adapt tools from the analysis of diffusion models, we take a different…

机器学习 · 统计学 2026-03-18 Lea Kunkel , Mathias Trabs

This manuscript introduces a regression-type formulation for approximating the Perron-Frobenius Operator by relying on distributional snapshots of data. These snapshots may represent densities of particles. The Wasserstein metric is…

最优化与控制 · 数学 2020-11-03 Amirhossein Karimi , Tryphon T. Georgiou

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

Model Updating is frequently used in Structural Health Monitoring to determine structures' operating conditions and whether maintenance is required. Data collected by sensors are used to update the values of some initially unknown…

统计计算 · 统计学 2024-01-23 Felipe Igea , Alice Cicirello

Flow matching (FM) has gained significant attention as a simulation-free generative model. Unlike diffusion models, which are based on stochastic differential equations, FM employs a simpler approach by solving an ordinary differential…

机器学习 · 计算机科学 2024-10-14 Kenji Fukumizu , Taiji Suzuki , Noboru Isobe , Kazusato Oko , Masanori Koyama

We construct a new random probability measure on the sphere and on the unit interval which in both cases has a Gibbs structure with the relative entropy functional as Hamiltonian. It satisfies a quasi-invariance formula with respect to the…

概率论 · 数学 2007-05-23 Max-K von Renesse , Karl-Theodor Sturm

Generative diffusion models are extensively used in unsupervised and self-supervised machine learning with the aim to generate new samples from a probability distribution estimated with a set of known samples. They have demonstrated…

流体动力学 · 物理学 2026-01-28 Wilfried Genuist , Éric Savin , Filippo Gatti , Didier Clouteau

In this paper, we study the problem of sampling from a distribution under the constraint of differential privacy (DP). Prior works measure the utility of DP sampling with density ratio-based measures such as KL divergence. However, such…

机器学习 · 统计学 2026-05-12 Shokichi Takakura , Seng Pei Liew , Satoshi Hasegawa

We prove that the sequence of marginals obtained from the iterations of the Sinkhorn algorithm or the iterative proportional fitting procedure (IPFP) on joint densities, converges to an absolutely continuous curve on the $2$-Wasserstein…

概率论 · 数学 2026-04-21 Nabarun Deb , Young-Heon Kim , Soumik Pal , Geoffrey Schiebinger

Denoising is intuitively related to projection. Indeed, under the manifold hypothesis, adding random noise is approximately equivalent to orthogonal perturbation. Hence, learning to denoise is approximately learning to project. In this…

机器学习 · 计算机科学 2024-06-04 Frank Permenter , Chenyang Yuan

This article details a novel numerical scheme to approximate gradient flows for optimal transport (i.e. Wasserstein) metrics. These flows have proved useful to tackle theoretically and numerically non-linear diffusion equations that model…

最优化与控制 · 数学 2015-03-10 Gabriel Peyré