Feature Learning for Bayesian Inference

Auf einen Blick

Projektleiter/in : Prof. Dr. Antonietta Mira
Co-Projektleiter/in : Prof. Dr. Fernando Perez-Cruz
Projektteam : Dr. Carlo Albert, Prof. Alessandro Laio, Prof. Jukka-Pekka Onnela, Dr. Simone Ulzega
Projektstatus : laufend
Drittmittelgeber : SNF
Kontaktperson : Simone Ulzega

Beschreibung

The goal of this project is to use interpretable Machine Learning (ML) to find low-dimensional features in high-dimensional noisy data generated by (i) stochastic models or (ii) real systems. In both cases, the problem is to disentangle the effect of high-dimensional disturbances, such as noise or unobserved inputs, from the effects of relevant characteristics (model parameters in the first case, system properties in the latter).

Publikationen

Ulzega, Simone; Albert, Carlo; Beer, Jürg,

2023.

Shedding light on the sun through the calibration of solar dynamo models on millennial records of solar activity.

In:

5th Swiss SCOSTEP Workshop, Windisch, Switzerland, 15-16 May 2023.

Verfügbar unter: http://scostep2023.cs.technik.fhnw.ch/pres/ulzega_scostep_2023.pdf
Bacci, Marco; Sukys, Jonas; Reichert, Peter; Ulzega, Simone; Albert, Carlo,

2023.

A comparison of numerical approaches for statistical inference with stochastic models.

Stochastic Environmental Research and Risk Assessment.

Verfügbar unter: https://doi.org/10.1007/s00477-023-02434-z
Ulzega, Simone; Albert, Carlo,

2023.

Boosting Bayesian parameter inference of SDE models by Hamiltonian scale separation : a real-world case study in urban hydrology.

In:

3rd biennial meeting of the ISBA Section on Bayesian Computation (Bayes Comp), Levi, Finnland, 15-17 March 2023.

Zurück