中文
相关论文

相关论文: Plug-in estimation of Schr\"odinger bridges

200 篇论文

In this paper we determine quantitative stability bounds for the Hessian of entropic potentials, \ie, the dual solution to the entropic optimal transport problem. To the authors' knowledge this is the first work addressing this second-order…

概率论 · 数学 2025-11-14 Giacomo Greco , Luca Tamanini

We develop a computationally tractable method for estimating the optimal map between two distributions over $\mathbb{R}^d$ with rigorous finite-sample guarantees. Leveraging an entropic version of Brenier's theorem, we show that our…

统计理论 · 数学 2024-05-14 Aram-Alexandre Pooladian , Jonathan Niles-Weed

For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few function evaluations. Flow matching and Schr\"odinger bridges define probability paths, yet their…

机器学习 · 计算机科学 2026-05-18 Bruno Trentini , Dejan Stancevic , Michael M. Bronstein , Alexander Tong , Luca Ambrogioni

The optimal transport problem has recently developed into a powerful framework for various applications in estimation and control. Many of the recent advances in the theory and application of optimal transport are based on regularizing the…

最优化与控制 · 数学 2021-03-12 Isabel Haasler , Axel Ringh , Yongxin Chen , Johan Karlsson

Mass transport problems arise in many areas of machine learning whereby one wants to compute a map transporting one distribution to another. Generative modeling techniques like Generative Adversarial Networks (GANs) and Denoising Diffusion…

机器学习 · 计算机科学 2024-09-17 Valentin De Bortoli , Iryna Korshunova , Andriy Mnih , Arnaud Doucet

The Entropic Optimal Transport (EOT) problem and its dynamic counterpart, the Schr\"odinger bridge (SB) problem, play an important role in modern machine learning, linking generative modeling with optimal transport theory. While recent…

Entropic optimal transport problems are regularized versions of optimal transport problems. These models play an increasingly important role in machine learning and generative modelling. For finite spaces, these problems are commonly solved…

机器学习 · 统计学 2025-12-30 O. Deniz Akyildiz , Pierre Del Moral , Joaquín Miguez

Entropic optimal transport problems play an increasingly important role in machine learning and generative modelling. In contrast with optimal transport maps which often have limited applicability in high dimensions, Schrodinger bridges can…

概率论 · 数学 2026-01-21 Pierre Del Moral , Ajay Jasra

This study employs a neural network that represents the solution to a Schr\"odinger bridge problem to perform super-resolution of 2-m temperature in an urban area. Schr\"odinger bridges generally describe transformations between two data…

大气与海洋物理 · 物理学 2025-12-15 Yuki Yasuda , Ryo Onishi

We propose and study a system of Schr\"odinger's problems and functional equations in probability theory. More precisely, we consider a system of variational problems of relative entropies for probability measures on a Euclidean space with…

概率论 · 数学 2025-06-17 Toshio Mikami , Jin Feng

In the early 1930's, Erwin Schroedinger, motivated by his quest for a more classical formulation of quantum mechanics, posed a large deviation problem for a cloud of independent Brownian particles. He showed that the solution to the problem…

最优化与控制 · 数学 2018-09-21 Montacer Essid , Michele Pavon

We consider the problem of sampling from an unknown distribution for which only a sufficiently large number of training samples are available. In this paper, we build on previous work combining Schr\"odinger bridges and plug & play Langevin…

机器学习 · 统计学 2024-11-19 Georg A. Gottwald , Sebastian Reich

We take a new look at the relation between the optimal transport problem and the Schr\"{o}dinger bridge problem from the stochastic control perspective. We show that the connections are richer and deeper than described in existing…

系统与控制 · 计算机科学 2014-12-16 Yongxin Chen , Tryphon Georgiou , Michele Pavon

The classical Schrodinger bridge seeks the most likely probability law for a diffusion process, in path space, that matches marginals at two end points in time; the likelihood is quantified by the relative entropy between the sought law and…

数学物理 · 物理学 2015-06-19 Tryphon T. Georgiou , Michele Pavon

We investigate the martingale Schr\"odinger bridge, recently introduced by Nutz and Wiesel as a distinguished martingale transport plan between two probability measures in convex order. We show that this construction extends naturally to…

概率论 · 数学 2026-05-14 Julio Backhoff , Mathias Beiglböck , Giorgia Bifronte , Armand Ley

Optimal transport (OT) serves as a natural framework for comparing probability measures, with applications in statistics, machine learning, and applied mathematics. Alas, statistical estimation and exact computation of the OT distances…

统计理论 · 数学 2024-05-14 Tao Wang , Ziv Goldfeld

Entropically regularized optimal transport between probability measures supported on compact subsets of Euclidean space admits a representation as an information projection under moment inequality constraints. Exploiting this structure, I…

统计理论 · 数学 2026-01-15 Rami V. Tabri

By directly integrating the Schroedinger starting in the transmission region and working backwards through the barrier, the tunneling probability can be determined for arbitrary potential barriers. The method employs techniques familiar to…

量子物理 · 物理学 2011-01-14 Andy Rundquist

Score-based diffusion models are frequently employed as structural priors in inverse problems. However, their iterative denoising process, initiated from Gaussian noise, often results in slow inference speeds. The Image-to-Image…

图像与视频处理 · 电气工程与系统科学 2024-07-08 Yuang Wang , Pengfei Jin , Siyeop Yoon , Matthew Tivnan , Quanzheng Li , Li Zhang , Dufan Wu

We establish the stability of solutions to the entropically regularized optimal transport problem with respect to the marginals and the cost function. The result is based on the geometric notion of cyclical invariance and inspired by the…

最优化与控制 · 数学 2022-07-07 Promit Ghosal , Marcel Nutz , Espen Bernton