AIConfPaper
← Search

Cornelius Schröder

6 accepted papers

2026

Scalable Simulation-Based Model Inference with Test-Time Complexity Control

Manuel Glöckler, Jose Pedro JP Manzano-Patron, Stamatios Sotiropoulos, Cornelius Schröder, Jakob Macke
ICML 2026poster

Simulation plays a central role in scientific discovery. In many applications, the bottleneck is no longer running a simulator—it is choosing among large families of plausible simulators, each corresponding to different forward models/hypotheses consistent with observations. Over large model familie…

Cited by 0Source ↗Scholar ↗
2025

FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators

Guy Moss, Leah Sophie Muhle, Reinhard Drews, Jakob H. Macke, Cornelius Schröder
NeurIPS 2025poster

Simulation-based inference (SBI) is an established approach for performing Bayesian inference on scientific simulators. SBI so far works best on low-dimensional parametric models. However, it is difficult to infer function-valued parameters, which frequently occur in disciplines that model spatiotem…

Cited by 0Source ↗Scholar ↗
2024

Simultaneous identification of models and parameters of scientific simulators

Cornelius Schröder, Jakob H. Macke
ICML 2024poster

Many scientific models are composed of multiple discrete components, and scientists often make heuristic decisions about which components to include. Bayesian inference provides a mathematical framework for systematically selecting model components, but defining prior distributions over model compon…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2024

Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation

Julius Vetter, Guy Moss, Cornelius Schröder, Richard Gao, Jakob H. Macke
NeurIPS 2024poster

Scientific modeling applications often require estimating a distribution of parameters consistent with a dataset of observations - an inference task also known as source distribution estimation. This problem can be ill-posed, however, since many different source distributions might produce the same…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2020

System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina

Cornelius Schröder, David Klindt, Sarah Strauss, Katrin Franke, Matthias Bethge, Thomas Euler +1
NeurIPS 2020spotlight

Visual processing in the retina has been studied in great detail at all levels such that a comprehensive picture of the retina's cell types and the many neural circuits they form is emerging. However, the currently best performing models of retinal function are black-box CNN models which are agnosti…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2019

Approximate Bayesian Inference for a Mechanistic Model of Vesicle Release at a Ribbon Synapse

Cornelius Schröder, Ben James, Leon Lagnado, Philipp Berens
NeurIPS 2019poster

The inherent noise of neural systems makes it difficult to construct models which accurately capture experimental measurements of their activity. While much research has been done on how to efficiently model neural activity with descriptive models such as linear-nonlinear-models (LN), Bayesian infer…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗