Martin Marek
I am a PhD student in Machine Learning at NYU, supervised by Andrew Gordon Wilson and Pavel Izmailov. I am interested in better understanding neural networks, especially from a probabilistic perspective.
Previously I studied Statistics and Machine Learning at UCL and interned as a Quant Researcher at QRT and ML Engineer at Snap.
Email me: martin.m@nyu.edu
Links
Personal projects
Publications
-
Can a Confident Prior Replace a Cold Posterior?
AABI workshop, 2024
[PDF, arXiv, GitHub] -
Image-based parking space occupancy classification: Dataset and baseline
arXiv preprint, 2021
[PDF, arXiv, GitHub] -
Physics of the mechanical toy Gee-Haw Whammy Diddle
Scientific Reports, 2018
[HTML, PDF]
Website design inspired by Pavel Izmailov.