May 18 – 22, 2026
Virginia Tech
America/New_York timezone

Learning Enhanced Ensemble Filters: Continuum Limits of Attention on Measures

May 19, 2026, 2:50 PM
25m
McBryde Hall 113 (Virginia Tech)

McBryde Hall 113

Virginia Tech

Minisymposium Talk Theoretical Advances in Operator Learning Theoretical Advances in Operator Learning

Speaker

Bohan Chen (California Institute of Technology)

Description

Many classic methods in data assimilation, like the Ensemble Kalman Filter (EnKF), are limited by its Gaussian ansatz. In this work, we frame the filtering update as learning a nonlinear operator mapping between probability distributions in the mean-field limit. We introduce Measure Neural Mappings (MNMs), a class of neural operators acting on probability measures, implemented via Set Transformers. A central theoretical contribution is establishing the continuum limit for attention mechanisms on measures. We prove that attention layers applied to finite ensembles are consistent with their continuous-measure counterparts, converging in Wasserstein distance as the sample size approaches infinity. This result rigorously links finite-dimensional linear algebra operations to infinite-dimensional operator learning, justifying the use of a single parameterization across different ensemble sizes. We demonstrate that the resulting MNM-enhanced ensemble filter (MNMEF) achieves superior accuracy on chaotic dynamical systems, including the Lorenz '96 and Kuramoto-Sivashinsky models, outperforming leading filtering methods.

Author

Bohan Chen (California Institute of Technology)

Co-authors

Prof. Andrew Stuart (California Institute of Technology) Mr Edoardo Calvello (California Institute of Technology) Dr Eviatar Bach (University of Reading) Dr Ricardo Baptista (University of Toronto)

Presentation materials

There are no materials yet.