← Back to all news
arXiv Machine Learning By Liyao Lyu, Xinyue Yu, Hayden Schaeffer

MVNN: A Measure-Valued Neural Network for Learning McKean-Vlasov Dynamics from Particle Data

Read the original on arXiv Machine Learning →

The paper introduces MVNN, a measure‑valued neural network designed to learn interaction forces in systems governed by McKean‑Vlasov dynamics directly from particle trajectory data. MVNN extends conventional neural networks to operate on probability measures by learning cylindrical features through an embedding network that maps distributions to scalable vector representations. The authors prove theoretical properties such as well‑posedness, propagation‑of‑chaos, universal approximation, and provide quantitative rates under low‑dimensional measure‑dependence, while demonstrating the method’s accuracy and strong out‑of‑distribution generalization on various first‑ and second‑order dynamical systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 23

DeepSPoC: A Deep Learning Based Sequential Propagation of Chaos

DeepSPoC is a neural particle method that replaces direct particle-particle interactions in sequential propagation of chaos (SPoC) with particle‑network interactions, using a neural density representation (KRnet) to approximate the empirical measure. By simulating particles in batches and embedding a neural network into the mean‑field SDE coefficients, DeepSPoC reduces memory usage and computational cost compared to traditional particle methods. The approach is demonstrated on various mean‑field equations, showing improved scalability for high‑dimensional problems.

By Kai Du, Yongle Xie, Tao Zhou, Yuancheng Zhou
More like this →
arXiv Machine Learning
Jun 4

Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks

arXiv:2602. 14885v2 Announce Type: replace-cross Abstract: Recurrent neural networks (RNNs) provide a theoretical framework for understanding computation in biological neural circuits, yet classical results, such as Hopfield's model of associative memory, rely on symmetric connectivity that restricts network dynamics to gradient-like flows.

By Ram\'on Nartallo-Kaluarachchi, Renaud Lambiotte, Alain Goriely
ragagentsdiffusion
More like this →
arXiv Machine Learning
Jul 17

RTS Smoother-Guided Learning of Physics-Based Neural Differential Models

arXiv:2607. 15180v1 Announce Type: new Abstract: Ordinary differential equations (ODEs) are widely used to model dynamical systems in physics, biology, neuroscience, and physiology, but in many applications some equations of the dynamics are unknown and only a subset of the state variables are measured.

By Ahmet Demirkaya, Georgios Stratis, Tales Imbiriba, Zachary D. Danziger, Deniz Erdogmus
benchmarks
More like this →
arXiv Machine Learning
Sep 23

Simulation-free Structure Learning for Stochastic Population Dynamics

arXiv:2510.16656v2 Announce Type: replace Abstract: Modeling dynamical systems and unraveling their underlying structural dependencies is central to many domains in the natural sciences. Various phys...

By Noah El Rimawi-Fine, Adam Stecklov, Lucas Nelson, Mathieu Blanchette, Alexander Tong, Stephen Y. Zhang, Lazar Atanackovic
More like this →