Gergely Flamich

PhD student, Machine Learning Group, Department of Engineering, University of Cambridge

Professional profile

Gergely Flamich is a PhD student in the Machine Learning Group at the Department of Engineering, University of Cambridge, under the supervision of José Miguel Hernández-Lobato since October 2020. Prior to his doctoral studies, Gergely completed an MPhil in Machine Learning and Machine Intelligence at the University of Cambridge and earned a Joint BSc (Hons) in Mathematics and Computer Science from the University of St Andrews.

His primary research interests involve developing and analysing data compression algorithms, particularly their application to neural data compression. He has a keen interest in exploring simulation methods for point processes, which have deep connections with data compression algorithms. His broader interests encompass generative and probabilistic modelling, including the use of variational autoencoders and diffusion models, as well as Bayesian optimisation.

Among his notable publications is the paper titled "Fast Relative Entropy Coding with A* Coding," co-authored with Stratis Markou and José Miguel Hernández-Lobato, which was presented at the 39th International Conference on Machine Learning in 2022.