English
Related papers

Related papers: Flow Matching: Markov Kernels, Stochastic Processe…

200 papers

Many systems in physics, engineering, and biology exhibit multiscale stochastic dynamics, where low-dimensional slow variables evolve under the influence of high-dimensional fast processes. In practice, observations are often limited to a…

Machine Learning · Statistics 2026-05-12 Anan Saha , Arnab Ganguly

We introduce Statistical Flow Matching (SFM), a novel and mathematically rigorous flow-matching framework on the manifold of parameterized probability measures inspired by the results from information geometry. We demonstrate the…

Machine Learning · Computer Science 2025-11-26 Chaoran Cheng , Jiahan Li , Jian Peng , Ge Liu

Diffusion-based models on continuous spaces have seen substantial recent progress through the mathematical framework of gradient flows, leveraging the Wasserstein-2 (${W}_2$) metric via the Jordan-Kinderlehrer-Otto (JKO) scheme. Despite the…

Machine Learning · Computer Science 2026-04-14 Dario Rancati , Jan Maas , Francesco Locatello

Continuous normalizing flows (CNFs) learn an ordinary differential equation to transform prior samples into data. Flow matching (FM) has recently emerged as a simulation-free approach for training CNFs by regressing a velocity model towards…

Machine Learning · Statistics 2024-05-28 Tianyu Xie , Yu Zhu , Longlin Yu , Tong Yang , Ziheng Cheng , Shiyue Zhang , Xiangyu Zhang , Cheng Zhang

Markov chains and diffusion processes are indispensable tools in machine learning and statistics that are used for inference, sampling, and modeling. With the growth of large-scale datasets, the computational cost associated with simulating…

Statistics Theory · Mathematics 2017-08-31 Jonathan H. Huggins , James Zou

A popular method to perform adversarial attacks on neuronal networks is the so-called fast gradient sign method and its iterative variant. In this paper, we interpret this method as an explicit Euler discretization of a differential…

Machine Learning · Computer Science 2025-09-17 Lukas Weigand , Tim Roith , Martin Burger

We study the problem of training a flow-based generative model, parametrized by a two-layer autoencoder, to sample from a high-dimensional Gaussian mixture. We provide a sharp end-to-end analysis of the problem. First, we provide a tight…

Machine Learning · Statistics 2024-08-20 Hugo Cui , Florent Krzakala , Eric Vanden-Eijnden , Lenka Zdeborová

In this work we explore the advantages of end-to-end learning of multilayer maps offered by feed forward neural-networks (FFNN) for learning and predicting dynamics from transient fluid flow data.While machine learning in general depends on…

Computational Physics · Physics 2020-10-28 Shivakanth Chary Puligilla , Balaji Jayaraman

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…

Computation · Statistics 2025-12-18 Sahil Bhola , Karthik Duraisamy

We introduce Generator Matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes. Generators characterize the infinitesimal evolution of a Markov process, which we leverage for generative modeling in a…

Machine Learning · Computer Science 2025-02-28 Peter Holderrieth , Marton Havasi , Jason Yim , Neta Shaul , Itai Gat , Tommi Jaakkola , Brian Karrer , Ricky T. Q. Chen , Yaron Lipman

Reconstructing near-wall turbulence from wall-based measurements is a critical yet inherently ill-posed problem in wall-bounded flows, where limited sensing and spatially heterogeneous flow-wall coupling challenge deterministic estimation…

Fluid Dynamics · Physics 2025-04-22 Meet Hemant Parikh , Xiantao Fan , Jian-Xun Wang

Learning generative models is challenging for a network edge node with limited data and computing power. Since tasks in similar environments share model similarity, it is plausible to leverage pre-trained generative models from the cloud or…

Machine Learning · Computer Science 2021-01-25 Mehmet Dedeoglu , Sen Lin , Zhaofeng Zhang , Junshan Zhang

Unconditional flow-matching trains diffusion models to transport samples from a source distribution to a target distribution by enforcing that the flows between sample pairs are unique. However, in conditional settings (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 George Stoica , Vivek Ramanujan , Xiang Fan , Ali Farhadi , Ranjay Krishna , Judy Hoffman

Gaussian process regression has proven very powerful in statistics, machine learning and inverse problems. A crucial aspect of the success of this methodology, in a wide range of applications to complex and real-world problems, is…

Statistics Theory · Mathematics 2021-03-18 Yifan Chen , Houman Owhadi , Andrew M. Stuart

Stochastic processes generated by non-stationary distributions are difficult to represent with conventional models such as Gaussian processes. This work presents Recurrent Autoregressive Flows as a method toward general stochastic process…

Machine Learning · Computer Science 2020-06-20 John Mern , Peter Morales , Mykel J. Kochenderfer

The success of autoregressive models largely depends on the effectiveness of vector quantization, a technique that discretizes continuous features by mapping them to the nearest code vectors within a learnable codebook. Two critical issues…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Xianghong Fang , Litao Guo , Hengchao Chen , Yuxuan Zhang , XiaofanXia , Dingjie Song , Yexin Liu , Hao Wang , Harry Yang , Yuan Yuan , Qiang Sun

Rectified Flows learn ODE vector fields whose trajectories are straight between source and target distributions, enabling near one-step inference. We show that this straight-path objective conceals fundamental failure modes: under…

Machine Learning · Computer Science 2025-10-22 Teodora Reu , Sixtine Dromigny , Michael Bronstein , Francisco Vargas

This notebook tutorial demonstrates a method for sampling Boltzmann distributions of lattice field theories using a class of machine learning models known as normalizing flows. The ideas and approaches proposed in arXiv:1904.12072,…

This work addresses the problem of learning the dynamics of high-dimensional probability densities over time using unlabeled samples, without assuming access to trajectory information. We introduce two-parameter flows that learn only…

Machine Learning · Computer Science 2026-05-27 Paul Schwerdtner , Tobias Blickhan , Benjamin Peherstorfer

We present two novel generative geometric deep learning frameworks, termed Flow Matching PointNet and Diffusion PointNet, for predicting fluid flow variables on irregular geometries by incorporating PointNet into flow matching and diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Ali Kashefi