About me
I am a research scientist at the Dalle Molle Institute for Artificial Intelligence (IDSIA USI-SUPSI), where I am affiliated with the UBS-IDSIA AI Lab. Previously, I was with the Amazon Machine Learning and Forecasting Team in Berlin, and was a postdoctoral researcher at the School of Engineering, École Polytechnique Fédérale de Lausanne (EPFL).
I received my PhD in Computer Science from EPFL in 2025.
My research focuses on machine learning, signal processing, network science and causality. For more details, please find my C.V. here (last updated December 2024).
Contact: firstname [dot] lastname [at] idsia [dot] ch
Selected Publications
Mert Kayaalp and Oleg Szehr, Signal recovery from time and frequency samples, arXiv:2603.16242
Mert Kayaalp, Caner Turkmen, Oleksandr Shchur et al., Test-time efficient pretrained model porfolios for time series forecasting, ICLR 2026
Mert Kayaalp and Ali H. Sayed, Causal influences over social learning networks, arXiv:2307.09575