Research in mathematical foundations of Data Science focuses on adapting mathematical principles to develop novel techniques to extract insights from data.
The underlying mathematical principles that support the models and algorithms used in data science encompass a broad range of mathematical disciplines that help understand, manipulate, and extract insights from data. These foundations are critical for designing effective algorithms, modelling big data, interpreting results, and ensuring the robustness and reliability of data-driven solutions.
Our research in this area includes, but is not limited to, numerical and mathematical optimization, statistical foundations of generative deep learning, topological pattern recognition, distance measure –based methods for statistical inference, network analysis, spatio-temporal analysis for event detection, and information geometry. We collaborate with theorists and other partners to include novel mathematical topics within the Data Science ecosystem.