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

Latent Twin Operator

May 18, 2026, 4:35 PM
25m
Torgersen Hall 1030 (Virginia Tech)

Torgersen Hall 1030

Virginia Tech

Minisymposium Talk Computational Advances in Discrete Inverse Problems Computational Advances in Discrete Inverse Problems

Speaker

Riley Yizhou Chen (Emory University)

Description

Learning solution operators in a manner that is independent of discretization and resolution remains a central challenge in data-driven modeling. The latent twins framework addresses this problem by constructing operators in a task-adaptive latent space for inverse problems and differential equations. However, in its classical form, latent twins relies on autoencoder architectures that are tied to fixed discretizations, coupling representation learning to a particular grid or resolution.

We address this limitation by separating state information from coordinate information. The latent variables encode the global system state, while a coordinate-conditioned decoder acts as an evaluation operator that reconstructs the state at arbitrary spatial or temporal locations through a family of linear or nonlinear maps. This viewpoint naturally supports sparse, irregular, and multi-resolution data, and connects latent twins to operator learning and reduced-order modeling perspectives. The resulting framework is well suited for applications in imaging, inverse problems, and the reduced-order modeling of time-dependent systems.

Authors

Dr Deepanshu Verma (Clemson University) Dr Joseph Lee Hart (Sandia National Laboratories) Dr Matthias Chung (Emory University) Riley Yizhou Chen (Emory University)

Presentation materials

There are no materials yet.