ANDRZEJ KAŁUŻA

research-and-teaching assistant

Faculty of Applied Mathematics
AGH University of Science and Technology
al. Mickiewicza 30
30-059 Kraków, Poland

About Me


I am currently research-and-teaching assistant at the Faculty of Applied Mathematics, AGH University of Science and Technology.

I am mostly interested in the numerical analysis and the complexity (in the sense of Information-Based Complexity) of continuous problems connected to stochastic analysis. My research is mainly conducted within the approximation of stochastic problems.

Currently, I am Team Leader of Data Scientists Departament in company connected with application predictive maintance in industry. I have a theoretical and practical knowledge in the fields of artificial intelligence, machine learning, data science, time series, deep learning, stochastic analysis and numerical methods.

In addition to ML experience, I participate in the international AGH-NVIDIA project on construction and analysis of algorithms for approximate solving of SDEs together with its efficient implementation on GPU NVIDIA graphics cards (parallel computation - mostly CUDA). One of the outcomes of the project is going to be a library (written in CUDA C) dedicated for GPU-powered computations.

Lectures

Model Blacka Scholesa

Analiza Matematyczna

Wstęp do analizy numerycznej

Applied Java

Publication

Optimal algorithms for solving stochastic initial-value problems with jumps

Andrzej KAŁUŻA, Doctoral dissertation

Optimal approximation of stochastic integrals in analytic noise model

Andrzej KAŁUŻA, Paweł M. MORKISZ, Paweł PRZYBYŁOWICZ, Applied Mathematics and Computation, ISSN 0096-3003. — 2019 vol. 356, s. 74–91.

Optimal global approximation of jump-diffusion SDEs via path-independent step-size control

Andrzej KAŁUŻA, Paweł PRZYBYŁOWICZ, Applied Numerical Mathematics ; ISSN 0168-9274. — 2018 vol. 128, s. 24–42.

Posters

Hybrid option pricing through AI and GPU-powered SDEs solvers

Tomasz Bochacik, Natalia Czyżewska, Andrzej Kałuża, Dawid Majchrowski, Paweł Morkisz, Paweł Przybyłowicz, Marcelina Studzińska-Wrona, NVIDIA's GPU Technology Conference (GTC), San Jose, USA} Poster - ONLINE

Contact