% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@MISC{Bazarova:1052328,
author = {Bazarova, Alina and Robledo, Jose Ignacio and Kesselheim,
Stefan},
title = {{I}ntroduction to {S}imulation {B}ased {I}nference:
enhancing synthetic models with {A}rtificial {I}ntelligence},
reportid = {FZJ-2026-00936},
year = {2025},
abstract = {n the world of the research fields drifting further apart
from one another and Artificial Intelligence (AI) tools
gaining increasingly more attention, methods which can bring
a number of seemingly disjoint fields together is of the
utmost importance. The proposed tutorial is sought to
provide researchers with an instrument to unify Bayesian
modelling, large-scale simulations, and AI methods while
integrating them into the HPC environment.While Bayesian
inference is widely used in the research community, as it
provides distributional estimates of model parameters and
allows to update the model by incorporating new data into
it, it often suffers from computationally intensive
processes and limited parallelization capabilities.
Simulation Based Inference (SBI) is a tool to tackle this
issue.SBI employs AI-based approximate Bayesian computation
to dramatically reduce inference times and generate reliable
estimates, even when observed data are sparse. This approach
enables any representative simulation model to inform
parameter constraints, yielding approximate posterior
distributions. Additionally, SBI facilitates workload
distribution across high-performance computing clusters,
further reducing runtime.This tutorial discusses theoretical
foundations and provides practical training for constructing
SBI frameworks tailored to specific models. Through provided
examples, participants will gain insight into various levels
of model granularity, ranging from a simple black box
approach to a highly customizable design, and develop the
skills to effectively manage HPC devices within a given
set-up. By participating in this tutorial, attendees will
gain an understanding of the principles of Simulation Based
Inference, learn how to apply this methodology in the
context of HPC in a variety of case scenarios, to evaluate
its potential and utility, and be encouraged to consider its
applicability to their own research projects.},
month = {Jun},
date = {2025-06-02},
organization = {Karlsruhe (Germany), 2 Jun 2025 - 2
Jun 2025},
subtyp = {Other},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
and Research Groups (POF4-511) / Helmholtz AI Consultant
Team FB Information (E54.303.11)},
pid = {G:(DE-HGF)POF4-5112 / G:(DE-Juel-1)E54.303.11},
typ = {PUB:(DE-HGF)17},
url = {https://juser.fz-juelich.de/record/1052328},
}