University of Oxford
Closing Date: 26th February 2021
Applications are invited for a full-time postdoctoral research assistant in computational statistics and statistical machine learning to work on the development and theoretical analysis of novel scalable methods for inference and learning.
For challenging high-dimensional problems, standard inference techniques such as Markov chain Monte Carlo methods are too computational intensive. Techniques such as variational methods have become prominent but are much less well-understood theoretically. The objective of this project is to develop novel scalable methods for inference and learning in high-dimensional scenarios and to analyze theoretically the resulting algorithms: consistency, non-asymptotic generalization bounds etc.
The main duties and responsibilities of the postholder will include conducting original research in the project area, developing novel scalable methods for Bayesian inference, developing theoretical and empirical frameworks for analysing the developed methodologies, publishing outcomes of research and disseminate research findings in talks at suitable seminars, workshops and conferences.
Applicants are sought who already have, or are close to the completion of, a doctorate in Applied Probability, Statistics or affiliated discipline. The successful candidate will have significant relevant experience in the development and study of inference and learning schemes and the ability to conduct and complete high-quality research independently, collaborate effectively with PIs and project partners. They will be able to communicate results effectively and supervise the research of DPhil students or junior researchers attached to the project.
Queries about the post should be addressed to Professor Arnaud Doucet at firstname.lastname@example.org.
This post is fixed-term for 18 months and no longer than 31 December 2022.
Only applications received before 12.00 midday on 26 February 2021 will be considered.
Interviews will be held on 15 March 2021.
For more information and to apply, click here.