Moritz Schauer — accepted AI-conference papers

2025

Score matching for bridges without learning time-reversals

Elizabeth Louise Baker, Moritz Schauer, Stefan Sommer

AISTATS 2025poster

We propose a new algorithm for learning a bridged diffusion process using score-matching methods. Our method relies on reversing the dynamics of the forward process and using this to learn a score function, which, via Doob's $h$-transform, gives us a bridged diffusion process; that is, a process co…

Cited by 0 Source ↗code ↗Scholar ↗

2022

Automatic Differentiation of Programs with Discrete Randomness

Gaurav Arya, Moritz Schauer, Frank Schäfer, Christopher Vincent Rackauckas

NeurIPS 2022accept

Automatic differentiation (AD), a technique for constructing new programs which compute the derivative of an original program, has become ubiquitous throughout scientific computing and deep learning due to the improved performance afforded by gradient-based optimization. However, AD systems have bee…

Cited by 51 Source ↗PDF ↗code ↗Scholar ↗