no code implementations • 26 Feb 2024 • Gordian Edenhofer, Philipp Frank, Jakob Roth, Reimar H. Leike, Massin Guerdi, Lukas I. Scheel-Platz, Matteo Guardiani, Vincent Eberle, Margret Westerkamp, Torsten A. Enßlin
Imaging is the process of transforming noisy, incomplete data into a space that humans can interpret.
no code implementations • 21 Jun 2022 • Gordian Edenhofer, Reimar H. Leike, Philipp Frank, Torsten A. Enßlin
Gaussian Processes (GPs) are highly expressive, probabilistic models.
no code implementations • 28 Oct 2021 • Johannes Zacherl, Philipp Frank, Torsten A. Enßlin
In this architecture, the latent space uncertainty is not generated using an additional information channel in the encoder, but derived from the decoder, by means of the Fisher information metric.
no code implementations • 21 May 2021 • Philipp Frank, Reimar Leike, Torsten A. Enßlin
Efficiently accessing the information contained in non-linear and high dimensional probability distributions remains a core challenge in modern statistics.
no code implementations • 14 Sep 2020 • Sara Milosevic, Philipp Frank, Reimar H. Leike, Ancla Müller, Torsten A. Enßlin
The three most significant feature maps encode astrophysical components: (1) The dense interstellar medium (ISM), (2) the hot and dilute regions of the ISM and (3) the CMB.
Instrumentation and Methods for Astrophysics High Energy Astrophysical Phenomena Data Analysis, Statistics and Probability
no code implementations • 26 Aug 2020 • Philipp Arras, Richard A. Perley, Hertzog L. Bester, Reimar Leike, Oleg Smirnov, Rüdiger Westermann, Torsten A. Enßlin
CLEAN, the commonly employed imaging algorithm in radio interferometry, suffers from a number of shortcomings: in its basic version it does not have the concept of diffuse flux, and the common practice of convolving the CLEAN components with the CLEAN beam erases the potential for super-resolution; it does not output uncertainty information; it produces images with unphysical negative flux regions; and its results are highly dependent on the so-called weighting scheme as well as on any human choice of CLEAN masks to guiding the imaging.
Instrumentation and Methods for Astrophysics Applications
2 code implementations • 30 Jan 2019 • Jakob Knollmüller, Torsten A. Enßlin
We propose Metric Gaussian Variational Inference (MGVI) as a method that goes beyond mean-field.
no code implementations • 24 Dec 2018 • Maximilian Kurthen, Torsten A. Enßlin
We address the problem of two-variable causal inference without intervention.
no code implementations • 11 Dec 2018 • Jakob Knollmüller, Torsten A. Enßlin
This transformation is a special form of the reparametrization trick, flattens the hierarchy and leads to a standard Gaussian prior on all resulting parameters.
no code implementations • 26 Dec 2016 • Torsten A. Enßlin, Jakob Knollmüller
The inference of correlated signal fields with unknown correlation structures is of high scientific and technological relevance, but poses significant conceptual and numerical challenges.
no code implementations • 27 Oct 2016 • Reimar H. Leike, Torsten A. Enßlin
The loss function that is obtained in the derivation is equal to the Kullback-Leibler divergence when normalized.
1 code implementation • 10 Apr 2015 • Sebastian Dorn, Torsten A. Enßlin
Matrix determinants play an important role in data analysis, in particular when Gaussian processes are involved.
Data Analysis, Statistics and Probability Instrumentation and Methods for Astrophysics Computation Methodology
no code implementations • 23 Oct 2014 • Sebastian Dorn, Torsten A. Enßlin, Maksim Greiner, Marco Selig, Vanessa Boehm
The calibration of a measurement device is crucial for every scientific experiment, where a signal has to be inferred from data.
no code implementations • 4 Dec 2013 • Torsten A. Enßlin, Henrik Junklewitz, Lars Winderling, Maksim Greiner, Marco Selig
Contemporary self-calibration schemes try to find a self-consistent solution for signal and calibration by exploiting redundancies in the measurements.
no code implementations • 18 Jan 2013 • Marco Selig, Michael R. Bell, Henrik Junklewitz, Niels Oppermann, Martin Reinecke, Maksim Greiner, Carlos Pachajoa, Torsten A. Enßlin
NIFTY, "Numerical Information Field Theory", is a software package designed to enable the development of signal inference algorithms that operate regardless of the underlying spatial grid and its resolution.
Instrumentation and Methods for Astrophysics Information Theory Mathematical Software Mathematical Physics Information Theory Mathematical Physics Data Analysis, Statistics and Probability Computation