中文
相关论文

相关论文: FalconBC: Flow matching for Amortized inference of…

200 篇论文

Modelling the vascular transport and adhesion of man-made particles is crucial for optimizing their efficacy in the detection and treatment of diseases. Here, a Lattice Boltzmann and Immersed Boundary methods are combined together for…

流体动力学 · 物理学 2016-06-07 Alessandro Coclite , Marco Donato de Tullio , Giuseppe Pascazio , Paolo Decuzzi

This work extends the input-output approach to the study of wall-bounded shear flows manipulated using actuators common in experimental flow control studies. In particular, we adapt this powerful analytical framework to investigate the flow…

流体动力学 · 物理学 2021-05-12 Igal Gluzman , Dennice F. Gayme

Learning-based model predictive control has been widely applied in autonomous racing to improve the closed-loop behaviour of vehicles in a data-driven manner. When environmental conditions change, e.g., due to rain, often only the…

Flow matching (FM) constructs continuous-time ODE samplers by prescribing probability paths between a base distribution and a target distribution. In this note, we study FM through the lens of finite-sample plug-in estimation. In addition…

机器学习 · 统计学 2026-05-15 Soon Hoe Lim

Learning probabilistic surrogates for partial differential equations remains challenging in data-scarce regimes: neural operators require large amounts of high-fidelity data, while generative approaches typically sacrifice resolution…

统计计算 · 统计学 2025-12-18 Sahil Bhola , Karthik Duraisamy

Accurate dose-response forecasting under sparse sampling is central to precision pharmacotherapy. We present the Amortized In-Context Mixed-Effect Transformer (AICMET) model, a transformer-based latent-variable framework that unifies…

机器学习 · 计算机科学 2026-01-21 César Ali Ojeda Marin , Wilhelm Huisinga , Purity Kavwele , Ramsés J. Sánchez , Niklas Hartung

Advances in computational science offer a principled pipeline for predictive modeling of cardiovascular flows and aspire to provide a valuable tool for monitoring, diagnostics and surgical planning. Such models can be nowadays deployed on…

机器学习 · 计算机科学 2019-09-19 Georgios Kissas , Yibo Yang , Eileen Hwuang , Walter R. Witschey , John A. Detre , Paris Perdikaris

Machine-learning based methods like physics-informed neural networks and physics-informed neural operators are becoming increasingly adept at solving even complex systems of partial differential equations. Boundary conditions can be…

数值分析 · 数学 2025-10-29 Niklas Göschel , Sebastian Götschel , Daniel Ruprecht

Coronary artery bypass grafts (CABG) surgery is an invasive procedure performed to circumvent partial or complete blood flow blockage in coronary artery disease (CAD). In this work, we apply a numerical optimal flow control model to…

Key-point-based scene understanding is fundamental for autonomous driving applications. At the same time, optical flow plays an important role in many vision tasks. However, due to the implicit bias of equal attention on all points, classic…

计算机视觉与模式识别 · 计算机科学 2023-09-25 Zhonghua Yi , Hao Shi , Kailun Yang , Qi Jiang , Yaozu Ye , Ze Wang , Huajian Ni , Kaiwei Wang

We consider the numerical integration of Langevin equations for particles in a channel, in the presence of boundary conditions fixing the concentration values at the ends. This kind of boundary condition appears for instance when…

计算物理 · 物理学 2020-07-24 Laureano Ramírez-Piscina

Time-series forecasting is crucial for numerous real-world applications including weather prediction and financial market modeling. While temporal-domain methods remain prevalent, frequency-domain approaches can effectively capture…

机器学习 · 计算机科学 2025-08-05 Zhixuan Li , Naipeng Chen , Seonghwa Choi , Sanghoon Lee , Weisi Lin

Wall-bounded turbulent flows are chaotic and multiscale, rendering real-time prediction at high Reynolds numbers computationally prohibitive in applications such as wind farms. Classical data assimilation methods are based on repeated…

流体动力学 · 物理学 2026-05-25 Fabian Steinbrenner , Baris Turan , Hao Teng , Heng Xiao

Data streams in real-world industrial scenarios often contain transitional operating conditions that are uncovered during offline training, leading to significant distribution shifts. To bridge the gap between static offline models and…

系统与控制 · 电气工程与系统科学 2026-05-26 Hongshuo Zhao , Zeyi Liu , Xiao He

We introduce a simulation-based, amortised Bayesian inference scheme to infer the parameters of random walks. Our approach learns the posterior distribution of the walks' parameters with a likelihood-free method. In the first step a graph…

Amortized Bayesian inference trains neural networks to solve stochastic inference problems using model simulations, thereby making it possible to rapidly perform Bayesian inference for any newly observed data. However, current…

机器学习 · 计算机科学 2024-07-16 Manuel Gloeckler , Michael Deistler , Christian Weilbach , Frank Wood , Jakob H. Macke

Objective: we propose a procedure for calibrating 4 parameters governing the mechanical boundary conditions (BCs) of a thoracic aorta (TA) model derived from one patient with ascending aortic aneurysm. The BCs reproduce the visco-elastic…

Bayesian predictive inference propagates parameter uncertainty to quantities of interest through the posterior-predictive distribution. In practice, this is typically performed using a two-stage procedure: first approximating the posterior…

机器学习 · 统计学 2026-05-06 Nan Feng , Xun Huan

Bayesian inference often faces a trade-off between computational speed and sampling accuracy. We propose an adaptive workflow that integrates rapid amortized inference with gold-standard MCMC techniques to achieve a favorable combination of…

机器学习 · 计算机科学 2026-02-19 Chengkun Li , Aki Vehtari , Paul-Christian Bürkner , Stefan T. Radev , Luigi Acerbi , Marvin Schmitt

Causal sensitivity analysis aims to provide bounds for causal effect estimates in the presence of unobserved confounding. However, existing methods for causal sensitivity analysis are per-instance procedures, meaning that changes to the…