Simon Schmitz
Master Thesis @Scientific Computing Center Des Kit Scc
Signup · Get unlimited contacts
WORK HISTORY
Master Thesis @Scientific Computing Center Des Kit Scc
Karlsruhe, DE
Thesis: Active learning via Bayesian Uncertainty Estimation with a costly data acquisition- Engineering a Bayesian Active learning framework for complex object detection architecture, implementing approximate Bayesian inference (VariationalBayesian Last Layer, MC Dropout, Evidential Deep Learning) to rigorously calibrate epistemic uncertainty for the regression localization task- Minimizing costly data labeling and acquisition processes in high-dimensional domains (SAR) to enable cost-effective, safe AI deployment.
EDUCATION
edX
Data Sciene: R Basics
Karlsruhe Institute of Technology (KIT)
Bachelor of Science - BS, Economathematics
Universidad Pontificia Bolivariana
Investigation Project, Research in Optimization Mathematics of Processes
Karlsruhe Institute of Technology (KIT)
Master of Science - MS, Economathematics
Hermann-Staudinger-Gymnasium
Abitur
ABOUT SIMON SCHMITZ
I am a Master\'s student in Economathematics at the Karlsruher Institute of Technology, specializing in Bayesian inference, uncertainty quantification, and financial engineering. My academic and professional work focuses on developing mathematically complex models and translating them into computationally efficient, real-world applications. I am particularly interested in problems involving- Bayesian machine learning & Active learning - Uncertainty quantification & probabilistic modeling - Stochastic simulation & Monte Carlo methods - Financial mathematics & derivative pricing.In my current Master\'s thesis, I develop a Bayesian active learning framework for complex object detection architectures, implementing approximate Bayesian inference (Bayesian last layer, MC Dropout) and information-theoretic acquisition strategies to reduce costly data labeling in high-dimensional settings.Alongside my research, I worked in quantitative model validation in instrumental pricing, benchmarking stochastic pricing engines, and validating FRTB sensitivities.I am motivated by intellectually challenging problems that require combining mathematical depth, structured reasoning, and robust software implementation. I value collaborative environments where complex ideas are discussed and translated into practical solutions.I am currently open to full-time opportunities in quantitative research, machine learning, and financial engineering starting from 01••••26.Skills: Bayesian Inference, Uncertainty Quantification, Monte Carlo Simulation, Stochastic Processes, Financial Engineering, Derivative Pricing, Model Validation, FRTB, Convex Optimization, Nonlinear Optimization, Markov Chain Monte Carlo, High-Performance Computing, Parallel Computing, Python, R, SQL, PyTorch, Polars, Pandas, Linux, Git, HPC
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.