arXiv subjects

Thorben Pieper-Sethmacher

Publications and source records attributed to Thorben Pieper-Sethmacher.

4 recordsLinked to original sources

arXiv2026

Infinite-dimensional generative diffusions via Doob's h-transform

This paper introduces a rigorous framework for defining generative diffusion models in infinite dimensions via Doob's h-transform. Rather than relying on time reversal of a noising process, a reference diffusion is forced towards the target distribution by an exponential change of measure. Compared to existing methodology, this approach readily generalises to the infinite-dimensional setting, hence offering greater flexibility in the diffusion model. The construction is derived rigorously under verifiable conditions, and bounds with respect to the target measure are established. We show that the forced process under the changed measure can be approximated by minimising a score-matching objective and validate our method on both synthetic and real data.

stat.ML↗

arXiv2025

Guided filtering and smoothing for infinite-dimensional diffusions

We consider the filtering and smoothing problems for an infinite-dimensional diffusion process X, observed through a finite-dimensional representation at discrete points in time. At the heart of our proposed methodology lies the construction of a path measure, termed the guided distribution of X, that is absolutely continuous with respect to the law of X, conditioned on the observations. We show that this distribution can be incorporated as a potent proposal measure for both sequential Monte Carlo as well as Markov Chain Monte Carlo schemes to tackle the filtering and smoothing problems respectively. In the offline setting, we extend our approach to incorporate parameter estimation of unknown model parameters. The proposed methodology is numerically illustrated in a case study for the stochastic Amari equation.

math.PR↗

arXiv2025

Simulation of infinite-dimensional diffusion bridges

Let X be the mild solution to a semilinear stochastic partial differential equation. In this article, we develop methodology to sample from the infinite-dimensional diffusion bridge that arises from conditioning X on a linear transformation LXT of the final state XT at some time T > 0. This solves a problem that has so far not been attended to in the literature. Our main contribution is the derivation of a path measure that is absolutely continuous with respect to the path measure of the infinite-dimensional diffusion bridge. This lifts previously known results for stochastic ordinary differential equations to the setting of infinite-dimensional diffusions and stochastic partial differential equations. We demonstrate our findings through numerical experiments on stochastic reaction-diffusion equations.

math.PR↗

arXiv2025

On a class of exponential changes of measure for stochastic PDEs

Given a mild solution $X$ to a semilinear stochastic partial differential equation (SPDE), we consider an exponential change of measure based on its infinitesimal generator $L$, defined in the topology of bounded pointwise convergence. The changed measure $\mathbb{P}^h$ depends on the choice of a function $h$ in the domain of $L$. In our main result, we derive conditions on $h$ for which the change of measure is of Girsanov-type. The process $X$ under $\mathbb{P}^h$ is then shown to be a mild solution to another SPDE with an extra additive drift-term. We illustrate how different choices of $h$ impact the law of $X$ under $\mathbb{P}^h$ in selected applications. These include the derivation of an infinite-dimensional diffusion bridge as well as the introduction of guided processes for SPDEs, generalizing results known for finite-dimensional diffusion processes to the infinite-dimensional case.

math.PR↗