中文
相关论文

相关论文: Diffusion on assortative networks: from mean-field…

200 篇论文

Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality.…

机器学习 · 计算机科学 2023-03-06 Raghav Singhal , Mark Goldstein , Rajesh Ranganath

Mean field approximation is a powerful technique to study the performance of large stochastic systems represented as $n$ interacting objects. Applications include load balancing models, epidemic spreading, cache replacement policies, or…

性能 · 计算机科学 2021-11-03 Sebastian Allmeier , Nicolas Gast

This paper investigates score-based diffusion models when the underlying target distribution is concentrated on or near low-dimensional manifolds within the higher-dimensional space in which they formally reside, a common characteristic of…

机器学习 · 计算机科学 2025-01-03 Gen Li , Yuling Yan

We consider the out-of-equilibrium dynamics of the Hamiltonian Mean Field (HMF) model, by focusing in particular on the properties of single-particle diffusion. As we shall here demonstrate analytically, if the autocorrelation of momenta in…

统计力学 · 物理学 2009-11-13 Andrea Antoniazzi , Duccio Fanelli , Stefano Ruffo

Handwritten Mathematical Expression Recognition (HMER) requires reasoning over diverse symbols and 2D structural layouts, yet autoregressive models struggle with exposure bias and syntactic inconsistency. We present a discrete diffusion…

计算机视觉与模式识别 · 计算机科学 2026-02-04 Takaya Kawakatsu , Ryo Ishiyama

This paper provides an $H_2$ optimal scheme for reducing diffusively coupled second-order systems evolving over undirected networks. The aim is to find a reduced-order model that not only approximates the input-output mapping of the…

最优化与控制 · 数学 2021-11-18 Lanlin Yu , Xiaodong Cheng , Jacquelien M. A. Scherpen , Junlin Xiong

We explain how to use diffusion models to learn inverse renormalization group flows of statistical and quantum field theories. Diffusion models are a class of machine learning models which have been used to generate samples from complex…

高能物理 - 理论 · 物理学 2023-09-07 Jordan Cotler , Semon Rezchikov

A broadcast mode may augment peer-to-peer overlay networks with an efficient, scalable data replication function, but may also give rise to a virtual link layer in VPN-type solutions. We introduce a simple broadcasting mechanism that…

网络与互联网体系结构 · 计算机科学 2009-05-25 Matthias Wählisch , Thomas C. Schmidt , Georg Wittenburg

The dynamics of ecological as well as chemical systems may depend on heterogeneous configurations. Heterogeneity in reaction-diffusion systems often increase modelling and simulating difficulties when non-linear effects are present. One…

物理与社会 · 物理学 2019-08-27 Orlando Silva

We present a quenched mean-field (QMF) theory for the dynamics of the susceptible-infected-susceptible (SIS) epidemic model on complex networks where dynamical correlations between connected vertices are taken into account by means of a…

生物物理 · 物理学 2013-09-11 Angélica S. Mata , Silvio C. Ferreira

The information flows among the people while they communicate through social media websites. Due to the dependency on digital media, a person shares important information or regular updates with friends and family. The set of persons on…

社会与信息网络 · 计算机科学 2024-06-14 Rahul Kumar Gautam , Anjeneya Swami Kare , Durga Bhavani S

The Mean Field Approximation (MFA), or continuum method, is often used in courses on Networks to derive the degree distribution of preferential attachment networks. This method is simple and the outcome is close to the correct answer.…

物理与社会 · 物理学 2020-06-25 Matthijs Ruijgrok

Deciphering the associations between network connectivity and nodal attributes is one of the core problems in network science. The dependency structure and high-dimensionality of networks pose unique challenges to traditional dependency…

统计方法学 · 统计学 2024-06-27 Youjin Lee , Cencheng Shen , Carey E. Priebe , Joshua T. Vogelstein

Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs. Existing methods for diffusion models typically require access to model gradients or retraining, limiting their…

机器学习 · 计算机科学 2025-10-17 Yutian Zhao , Chao Du , Xiaosen Zheng , Tianyu Pang , Min Lin

Diffusion models, which convert noise into new data instances by learning to reverse a diffusion process, have become a cornerstone in contemporary generative modeling. In this work, we develop non-asymptotic convergence theory for a…

机器学习 · 计算机科学 2024-08-06 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

This PhD thesis lays out algebraic and topological structures relevant for the study of probabilistic graphical models. Marginal estimation algorithms are introduced as diffusion equations of the form $\dot u = \delta \varphi$. They…

数学物理 · 物理学 2020-09-25 Olivier Peltre

A new ensemble filter that allows for the uncertainty in the prior distribution is proposed and tested. The filter relies on the conditional Gaussian distribution of the state given the model-error and predictability-error covariance…

数据分析、统计与概率 · 物理学 2016-12-19 Michael Tsyrulnikov , Alexander Rakitko

We study diffusion and consensus dynamics in a Network of Networks model. In this model, there is a collection of sub-networks, connected to one another using a small number of links. We consider a setting where the links between networks…

社会与信息网络 · 计算机科学 2020-02-17 Yuhao Yi , Anirban Das , Stacy Patterson , Bassam Bamieh , Zhongzhi Zhang

The spread of an epidemic is often modeled by an SIR random process on a social network graph. The MinINF problem for optimal social distancing involves minimizing the expected number of infections, when we are allowed to break at most $B$…

数据结构与算法 · 计算机科学 2022-02-18 Amy Babay , Michael Dinitz , Aravind Srinivasan , Leonidas Tsepenekas , Anil Vullikanti

Diffusion is a commonly used technique for spreading information from point to point on a graph. The rationale behind diffusion is not clear. And the multi-types Galton-Watson forest is a random model of population growth without space or…

社会与信息网络 · 计算机科学 2022-03-23 Yanjiao Zhu , Qilin Li , Wanquan Liu , Chuancun Yin , Zhenlong Gao