Assistant Professor of Computer Science, Aalto University
Follow Me on Twitter!
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 social media posts, mobility patterns and health-records. 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 is a precise link between network Lasso methods and network flow methods. See our preprint On the duality between network flows and network Lasso.
Some Selected News