Michael Lind Severinsen — accepted AI-conference papers

2025

Infinite-dimensional Diffusion Bridge Simulation via Operator Learning

Gefan Yang, Elizabeth Louise Baker, Michael Lind Severinsen, Christy Anna Hipsley, Stefan Sommer

AISTATS 2025poster

The diffusion bridge, which is a diffusion process conditioned on hitting a specific state within a finite period, has found broad applications in various scientific and engineering fields. However, simulating diffusion bridges for modeling natural data can be challenging due to both the intractabil…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Conditioning non-linear and infinite-dimensional diffusion processes

Elizabeth Louise Baker, Gefan Yang, Michael Lind Severinsen, Christy Anna Hipsley, Stefan Sommer

NeurIPS 2024spotlight

Generative diffusion models and many stochastic models in science and engineering naturally live in infinite dimensions before discretisation. To incorporate observed data for statistical and learning tasks, one needs to condition on observations. While recent work has treated conditioning linear pr…

Cited by 19 Source ↗PDF ↗Scholar ↗