Machine Learning for Big Data

Research
Our research revolves around machine learning models and methods for big data over networks. The data arising in many important big data applications, ranging from social networks to network medicine, consist of high-dimensional data points related by an intrinsic (complex) network structure. In order to jointly leverage the information conveyed in the network structure as well as the statistical power contained in high-dimensional data points, we study networked exponential families. 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.
Latest publications
Hercules
Towards Model-Agnostic Federated Learning over Networks
Wind to start the washing machine? High-Resolution Wind Atlas for Finland
Machine Learning
From Intuition to Reasoning
Images of Galois representations in mod p Hecke algebras
Learning optimal lattice codes for MIMO communications
Hash-Based Preprocessing and Inprocessing Techniques in SAT Solvers
Containing Future Epidemics With Trustworthy Federated Systems for Ubiquitous Warning and Response
Well-Rounded Lattices
People

Henrik Ambos

Laia Amorós Carafí
