Collaborative Data Science in Biomedicine
The Greater Data Science Cooperative Institute (GDSC) combines Cornell University’s and University of Rochester’s shared expertise in electrical engineering, mathematics, statistics, and theoretical computer science in solving foundational data science challenges in biomedicine and healthcare. The GDSC wants to forge a consensus perspective on data science that transcends any individual field, while overcoming real-world challenges in a specific application domain. By grounding its research in biomedicine, the GDSC ensures that its innovations in data science have a direct, positive impact on society.
Led by David S. Matteson, Statistics and Data Science/Social Statistics, the GDSC’s core team of 10 co-principal investigators will facilitate collaboration among a broad community of researchers through workshops, seminars, symposia, and educational initiatives.
The GDSC’s vision is to develop a mathematical foundation that integrates transdisciplinary perspectives and enables applications that benefit everyone worldwide.
GDSC is pursuing five cross-disciplinary research directions: topological data analysis (approaches to high-dimensional, incomplete, and noisy data); data representation (novel source models and distortion measures in biomedical imaging, genomics, and neural-spike training data); network and graph learning (structures to solve data problems intrinsic to non-homogenous populations); decisions, control, and dynamic learning (methods to improve health and disease management and facilitate dynamic treatment regimes); and diverse and complex modalities (for inference under computational and privacy constraints and for high-dimensional data without parametric model assumptions).