Alexander Jung

Assistant Professor of Computer Science, Aalto University

Follow Me on Twitter! Fork me on GitHub
Contact information Publications Teaching Short CV

My Top Achievements



My current research studies machine learning models and methods for massive amounts of network-structured data (``big data over networks''). Network-structured data arises, e.g., in epidemiology where data points represent humans which interact according to physical or social proximity. Each data point (human) is characterized by a vast number of features such as the personal data available on a smartphone. The challenge is to extract the most relevant information from this raw data while respecting privacy of individuals.

To jointly leverage the information conveyed by high-dimensional data points and their network structure, we have proposed networked exponential families (preprint here ). For the accurate learning of such networked exponential families, we borrow statistical strength, via the intrinsic network structure, across the dataset.

A powerful algorithmic toolbox for designing learning algorithms is provided by convex optimization methods. Modern convex optimization methods are appealing for big data applications as they can be implemented as highly scalable message passing protocols.

A recent key result obtained from our research are precise conditions on the network structure an available data such that accurate predictions can be obtained by efficient methods:
A. Jung and N. Tran. Localized Linear Regression in Networked Data. IEEE Sig. Proc. Letters , 2019. Preprint


 


Some Selected News


Selected Publications
Recent Talks and Lectures
first.last at aalto.fi