PhD Studentship: Bayesian Modeling of High-dimensional Structural Data

The University of Manchester is offering a 3.5-year fully funded PhD studentship within the Department of Mathematics. The research focuses on creating computationally efficient and scalable Bayesian learning methodologies to analyze high-dimensional observations in fields such as biological sciences, social science, and engineering. The successful candidate will investigate how structural dependencies, such as covariance structures and conditional dependency graphs, evolve over time. Applicants are expected to contribute to both the practical application and the theoretical foundation of these Bayesian frameworks.

• Develop comprehensive Bayesian learning frameworks for high-dimensional data structures.
• Design computationally efficient and scalable algorithms for complex data-generating mechanisms.
• Apply Bayesian methodologies to real-world problems in biological, social, or engineering sciences.
• Establish theoretical properties of the developed statistical models.
• Conduct independent research and document findings for academic publication.