Professor George Deligiannidis

Associate Professor of Statistics

Biographical Sketch

I studied Mathematics (MMath) at the University of Warwick and Financial Mathematics (MSc) at Heriot-Watt University and the University of Edinburgh. After obtaining my PhD from the School of Mathematical Sciences of the University of Nottingham under the supervision of Sergey Utev and Huiling Le, I moved to the Department of Mathematics of the University of Leicester as a Teaching Assistant/Fellow. In 2012 I moved to the Department of Statistics of the University of Oxford as Departmental Lecturer. I stayed in Oxford until September 2016 when I moved to the Department of Mathematics of King’s College London as Lecturer in Statistics. I moved back to the University of Oxford in December 2017 as Associate Professor of Statistics.

News

I recently received a New Investigator Award from EPSRC. I will be hiring a postdoc for three years to work on this project. If interested, you can apply here .

Research Interests

I work in the intersection of probability and statistics to analyse random processes and objects, especially those arising from algorithms used in computational statistics and machine learning. I have worked extensively on the theory and methodology of sampling methods, especially Markov Chain Monte Carlo. I have also worked on random walks on lattices and groups.
At the moment I am particularly interested in the interplay between sampling, optimization and machine learning.

Publications

Personal website
Deligiannidis, G., de Bortoli, V. and Doucet, A. (2024) “Quantitative uniform stability of the iterative proportional fitting procedure”, The Annals of Applied Probability, 34(1A).
Benton, J., Bortoli, V., Doucet, A. and Deligiannidis, G. (2023) “Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization”, in.
Dhillon, G., Deligiannidis, G. and Rainforth, T. (2023) “On the expected size of conformal prediction sets”, in. Journal of Machine Learning Research.
Williams, C., Falck, F., Deligiannidis, G., Holmes, C., Doucet, A. and Syed, S. (2023) “A Unified Framework for U-Net Design and Analysis”, arXiv.
Benton, J., Deligiannidis, G. and Doucet, A. (2023) “Error bounds for flow matching methods”, Transactions on Machine Learning Research [Preprint].
Falck, F., Williams, C., Danks, D., Deligiannidis, G., Yau, C., Holmes, C., Willetts, M. and Doucet, A. (2023) “A multi-resolution framework for U-nets with applications to hierarchical VAEs”, in Advances in Neural Information Processing Systems 35 (NeurIPS 2022). Curran Associates, pp. 15529–15544.
Campbell, A., Benton, J., De Bortoli, V., Rainforth, T., Deligiannidis, G. and Doucet, A. (2023) “A continuous time framework for discrete denoising models”, in Advances in Neural Information Processing Systems 35 (NeurIPS 2022). Curran Associates, pp. 28266–28279.
Dupuis, B., Deligiannidis, G. and Şimşekli, U. (2023) “Generalization Bounds with Data-dependent Fractal Dimensions”, arXiv.
Falck, F., Williams, C., Danks, D., Deligiannidis, G., Yau, C., Holmes, C., Doucet, A. and Willetts, M. (2023) “A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs”, arXiv.
Dupuis, B., Deligiannidis, G. and Şimşekli, U. (2023) “Generalization Bounds using Data-Dependent Fractal Dimensions”, in Proceedings of Machine Learning Research, pp. 8922–8968.

Publications

Deligiannidis, G., de Bortoli, V. and Doucet, A. (2024) “Quantitative uniform stability of the iterative proportional fitting procedure”, The Annals of Applied Probability, 34(1A).
Benton, J., Bortoli, V., Doucet, A. and Deligiannidis, G. (2023) “Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization”, in.
Dhillon, G., Deligiannidis, G. and Rainforth, T. (2023) “On the expected size of conformal prediction sets”, in. Journal of Machine Learning Research.
Williams, C., Falck, F., Deligiannidis, G., Holmes, C., Doucet, A. and Syed, S. (2023) “A Unified Framework for U-Net Design and Analysis”, arXiv.
Benton, J., Deligiannidis, G. and Doucet, A. (2023) “Error bounds for flow matching methods”, Transactions on Machine Learning Research [Preprint].
Falck, F., Williams, C., Danks, D., Deligiannidis, G., Yau, C., Holmes, C., Willetts, M. and Doucet, A. (2023) “A multi-resolution framework for U-nets with applications to hierarchical VAEs”, in Advances in Neural Information Processing Systems 35 (NeurIPS 2022). Curran Associates, pp. 15529–15544.
Campbell, A., Benton, J., De Bortoli, V., Rainforth, T., Deligiannidis, G. and Doucet, A. (2023) “A continuous time framework for discrete denoising models”, in Advances in Neural Information Processing Systems 35 (NeurIPS 2022). Curran Associates, pp. 28266–28279.
Dupuis, B., Deligiannidis, G. and Şimşekli, U. (2023) “Generalization Bounds with Data-dependent Fractal Dimensions”, arXiv.
Falck, F., Williams, C., Danks, D., Deligiannidis, G., Yau, C., Holmes, C., Doucet, A. and Willetts, M. (2023) “A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs”, arXiv.
Dupuis, B., Deligiannidis, G. and Şimşekli, U. (2023) “Generalization Bounds using Data-Dependent Fractal Dimensions”, in Proceedings of Machine Learning Research, pp. 8922–8968.

Contact Details

College Affiliation: Hugh Price Fellow at Jesus College

Email: deligian@stats.ox.ac.uk

Telephone: +44(0)1865 282851

Office number: 1.05

Graduate Students

Joe Benton

Amitis Shidani

Eugenio Clerico

Chris Williams

Angus Philips

Guneet Dhillon

James Thornton 

Research Groups

Computational Statistics and Machine Learning

Statistical Theory and Methodology