English
Related papers

Related papers: Ensemble Variational Fokker-Planck Methods for Dat…

200 papers

The theory of stochastic processes impacts both physical and social sciences. At the molecular scale, stochastic dynamics is ubiquitous because of thermal fluctuations. The Fokker-Plank-Smoluchowski equation models the time evolution of the…

Model error covariances play a central role in the performance of data assimilation methods applied to nonlinear state-space models. However, these covariances are largely unknown in most of the applications. A misspecification of the model…

Computation · Statistics 2019-11-06 María Magdalena Lucini , Peter Jan van Leeuwen , Manuel Pulido

This paper employs Bayesian probability theory for analyzing data generated in femtosecond pump-probe photoelectron-photoion coincidence (PEPICO) experiments. These experiments allow investigating ultrafast dynamical processes in…

Flow maps enable high-quality image generation in a single forward pass. However, unlike iterative diffusion models, their lack of an explicit sampling trajectory impedes incorporating external constraints for conditional generation and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Abbas Mammadov , So Takao , Bohan Chen , Ricardo Baptista , Morteza Mardani , Yee Whye Teh , Julius Berner

Gaussian Processes (GPs) can be used as flexible, non-parametric function priors. Inspired by the growing body of work on Normalizing Flows, we enlarge this class of priors through a parametric invertible transformation that can be made…

Machine Learning · Computer Science 2021-02-26 Juan Maroñas , Oliver Hamelijnck , Jeremias Knoblauch , Theodoros Damoulas

Normalizing flows provide an elegant approach to generative modeling that allows for efficient sampling and exact density evaluation of unknown data distributions. However, current techniques have significant limitations in their…

Machine Learning · Computer Science 2022-06-22 Sahil Sidheekh , Chris B. Dock , Tushar Jain , Radu Balan , Maneesh K. Singh

Sequential probabilistic inference from streaming observations requires modeling distributions over future trajectories as new observations arrive. Although diffusion and flow-matching models are effective at capturing high-dimensional,…

Machine Learning · Computer Science 2026-05-15 Yinan Huang , Hans Hao-Hsun Hsu , Junran Wang , Bo Dai , Pan Li

Motivated by the challenge of incorporating data into misspecified and multiscale dynamical models, we study a McKean-Vlasov equation that contains the data stream as a common driving rough path. This setting allows us to prove…

Probability · Mathematics 2023-12-15 Michele Coghi , Torstein Nilssen , Nikolas Nüsken , Sebastian Reich

Particle smoothers are widely used algorithms allowing to approximate the smoothing distribution in hidden Markov models. Existing algorithms often suffer from slow computational time or degeneracy. We propose in this paper a way to improve…

Methodology · Statistics 2011-07-28 Cyrille Dubarry , Randal Douc

We propose a novel framework for simulating ink as a particle-laden flow using particle flow maps. Our method addresses the limitations of existing flow-map techniques, which struggle with dissipative forces like viscosity and drag, thereby…

Graphics · Computer Science 2024-09-11 Zhiqi Li , Duowen Chen , Candong Lin , Jinyuan Liu , Bo Zhu

Ensemble calculations are essential for systems with uncertain data but require substantial increase in computational resources. This increase severely limits ensemble size. To reach beyond current limits, we present a first-order…

Numerical Analysis · Mathematics 2017-12-19 Joseph A. Fiordilino , Michael McLaughlin

High-energy, multi-component plasmas in which pair creation and annihilation, lepton-lepton scattering, lepton-proton scattering, and Comptonization all contribute to establishing the particle and photon distributions, are present in a…

Astrophysics · Physics 2014-10-13 Sergei Nayakshin , Fulvio Melia

Forecasting conditional stochastic nonlinear dynamical systems is a fundamental challenge repeatedly encountered across the biological and physical sciences. While flow-based models can impressively predict the temporal evolution of…

Machine Learning · Computer Science 2025-04-02 Adam P. Generale , Andreas E. Robertson , Surya R. Kalidindi

A fundamental macroscopic description of a magnetized plasma is the Vlasov equation supplemented by the nonlinear inverse-square force Fokker-Planck collision operator [Rosenbluth et al., Phys. Rev., 107, 1957]. The Vlasov part describes…

Plasma Physics · Physics 2015-09-30 Eero Hirvijoki , Jeff Candy , Emily Belli , Ola Embréus

The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of posterior approximations in order to allow for efficient inference,…

Machine Learning · Statistics 2016-06-15 Danilo Jimenez Rezende , Shakir Mohamed

Missing data is a common problem in real-world sensor data collection. The performance of various approaches to impute data degrade rapidly in the extreme scenarios of low data sampling and noisy sampling, a case present in many real-world…

Signal Processing · Electrical Eng. & Systems 2022-01-21 Charul Paliwal , Pravesh Biyani , Ketan Rajawat

We consider a Vicsek model of self-propelled particles with bounded confidence, where each particle interacts only with neighbors that have a similar direction. Depending on parameters, the system exhibits a continuous or discontinuous…

Statistical Mechanics · Physics 2017-05-22 Rüdiger Kürsten , Thomas Ihle

The orientational dynamics of weakly inertial axisymmetric particles in a steady flow is investigated. We derive an asymptotic equation of motion for the unit axial vector along the particle symmetry axis, valid for small Stokes number St,…

Fluid Dynamics · Physics 2014-05-22 J. Einarsson , J. R. Angilella , B. Mehlig

The propagation of light in a scattering medium is described as the motion of a special kind of a Brownian particle on which the fluctuating forces act only perpendicular to its velocity. This enforces strictly and dynamically the…

Disordered Systems and Neural Networks · Physics 2009-10-31 S. Anantha Ramakrishna , N. Kumar

State-space models can be used to incorporate subject knowledge on the underlying dynamics of a time series by the introduction of a latent Markov state-process. A user can specify the dynamics of this process together with how the state…

Computation · Statistics 2017-09-14 Paul Fearnhead , Hans Künsch