中文
相关论文

相关论文: Statistical Error Bounds for Generative Solvers of…

200 篇论文

Discrete time analogues of ergodic stochastic differential equations (SDEs) are one of the most popular and flexible tools for sampling high-dimensional probability measures. Non-asymptotic analysis in the $L^2$ Wasserstein distance of…

概率论 · 数学 2019-10-11 Mateusz B. Majka , Aleksandar Mijatović , Lukasz Szpruch

The robust statistical description of dynamical systems under perturbations is a central problem in ergodic theory. In this paper, we investigate the statistical properties of skew-product maps driven by a subshift of finite type with…

动力系统 · 数学 2026-03-23 Davi Lima , Rafael Lucena

Turbulence in wall-bounded flows is characterized by stable statistics. Although, in many turbulent systems, this stable statistical state corresponds to a stable fixed point of an associated statistical state dynamics (SSD) closed at…

流体动力学 · 物理学 2023-12-14 Brian F. Farrell , Petros J. Ioannou

Score-based generative models have emerged as a powerful approach for sampling high-dimensional probability distributions. Despite their effectiveness, their theoretical underpinnings remain relatively underdeveloped. In this work, we study…

机器学习 · 计算机科学 2025-04-22 Daniel Zhengyu Huang , Jiaoyang Huang , Zhengjiang Lin

We provide new convergence guarantees in Wasserstein distance for diffusion-based generative models, covering both stochastic (DDPM-like) and deterministic (DDIM-like) sampling methods. We introduce a simple framework to analyze…

机器学习 · 计算机科学 2025-11-14 Eliot Beyler , Francis Bach

Under general assumptions on the target distribution $p^\star$, we establish a sharp Lipschitz regularity theory for flow-matching vector fields and diffusion-model scores, with optimal dependence on time and dimension. As applications, we…

统计理论 · 数学 2026-04-08 Arthur Stéphanovitch

ODE solvers with randomly sampled timestep sizes appear in the context of chaotic dynamical systems, differential equations with low regularity, and, implicitly, in stochastic optimisation. In this work, we propose and study the stochastic…

数值分析 · 数学 2024-08-05 Jonas Latz

In this article, we consider the problem of sampling from a probability measure $\pi$ having a density on $\mathbb{R}^d$ known up to a normalizing constant, $x\mapsto \mathrm{e}^{-U(x)} / \int_{\mathbb{R}^d} \mathrm{e}^{-U(y)} \mathrm{d}…

统计方法学 · 统计学 2018-11-27 Nicolas Brosse , Alain Durmus , Éric Moulines , Sotirios Sabanis

A recent Letter by Oberlack et al. [Phys. Rev. Lett. 128, 024502 (2022)] claims to have derived new symmetry-induced solutions of the non-modelled statistical Navier-Stokes equations of turbulent channel flow. A high accuracy match to DNS…

流体动力学 · 物理学 2023-02-13 Michael Frewer , George Khujadze

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

Strongly nonlinear flows, which commonly arise in geophysical and engineering turbulence, are characterized by persistent and intermittent energy transfer between various spatial and temporal scales. These systems are difficult to model and…

动力系统 · 数学 2022-01-25 Hassan Arbabi , Themistoklis Sapsis

In this paper, we study the numerical discretization of stochastic differential equations with locally Lipschitz, super-linearly growing drift, and the resulting implications for sampling from non-log-concave distributions satisfying a…

概率论 · 数学 2026-05-26 Iosif Lytras , Angelos Ntousis

Many statistical estimators are defined as the fixed point of a data-dependent operator, with estimators based on minimizing a cost function being an important special case. The limiting performance of such estimators depends on the…

机器学习 · 计算机科学 2022-03-22 Nhat Ho , Koulik Khamaru , Raaz Dwivedi , Martin J. Wainwright , Michael I. Jordan , Bin Yu

A simplified thermodynamic approach of the incompressible 2D Euler equation is considered based on the conservation of energy, circulation and microscopic enstrophy. Statistical equilibrium states are obtained by maximizing the…

流体动力学 · 物理学 2011-04-12 A. Naso , P. H. Chavanis , B. Dubrulle

Despite the remarkable empirical success of generative models, the available theory on their statistical accuracy in scientific computing remains largely pessimistic. This paper develops a theoretical framework for understanding the…

机器学习 · 计算机科学 2026-05-21 Likun Lin , Zhongjian Wang , Jack Xin , Zhiwen Zhang

We propose and study the framework of dissipative statistical solutions for the incompressible Euler equations. Statistical solutions are time-parameterized probability measures on the space of square-integrable functions, whose…

数值分析 · 数学 2021-02-25 Samuel Lanthaler , Siddhartha Mishra , Carlos Parés-Pulido

Optimal transport provides an inherently geometric and highly structured framework for studying spaces of probability measures, supplying a rich theoretical toolkit for contemporary statistics, machine learning, and generative modelling. In…

统计理论 · 数学 2026-05-21 Riccardo Passeggeri , Rohan M. Shenoy , Pengcheng Ye

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

This paper develops a generative model by minimizing the second-order Wasserstein loss (the $W_2$ loss) through a distribution-dependent ordinary differential equation (ODE), whose dynamics involves the Kantorovich potential associated with…

机器学习 · 统计学 2026-05-14 Yu-Jui Huang , Zachariah Malik

Steady statistics of a passive scalar advected by a random two-dimensional flow of an incompressible fluid is described in the range of scales between the correlation length of the flow and the diffusion scale. That corresponds to the…

凝聚态物理 · 物理学 2009-10-22 M. Chertkov , G. Falkovich , I. Kolokolov , V. Lebedev
‹ 上一页 1 2 3 10 下一页 ›