���ʵ���

's research revolves around sparse models and machine learning for big data with a focus on trade-offs between computational as well as communication complexity on one hand, and the learning performance on the other hand. In particular, he is interested in the efficient and distributed processing of high-dimensional networked datasets occurring, e.g., in social networks, genetics or wireless sensor networks. Together with his collaborators, he recently derived fundamental limits and efficient algorithms for graphical model selection and dictionary learning for such high-dimensional datasets. His research can be useful when it comes to detecting frauds in online auction systems or understanding the interplay between genes and particular diseases.

The quality of his research is documented by several publications in first-class journals such as IEEE Transactions on Information Theory, IEEE Signal Processing Letters and IEEE Transactions on Signal Processing. 

Alex Jung received his Dr. techn. degree in statistical signal processing from Vienna University of Technology in 2011. After working 6 months as a Post-Doc at ETH Zurich, he became Assistant Professor (non-tenure track) at Vienna University of Technology in 2013. He spent research visits at University of Edinburgh in 2013 and University of Michigan in 2014.

He received several national and international awards including a best student paper award at the world’s largest conference on signal processing, IEEE ICASSP 2011 in Prague.