Thomas Berrett

alt text 

Department of Statistics
University of Warwick
Coventry
CV4 7AL
United Kingdom
Email: tom.berrett [@] warwick [DOT] ac [DOT] uk

About me

I am currently an Assistant Professor at the Department of Statistics, University of Warwick. Until July 2020, I was a postdoctoral researcher at CREST, ENSAE, Institut Polytechnique de Paris supervised by Prof. Cristina Butucea. Until August 2019 I was postdoctoral researcher supervised by Prof. Richard J. Samworth, in the Statistical Laboratory, a subdepartment of the Department of Pure Mathematics and Mathematical Statistics at the University of Cambridge, and was affiliated with the StatScale programme. In January 2018 I graduated with my PhD which I worked on under the supervision of Prof Richard J. Samworth.

From July 2022 my research has been supported by an EPSRC New Investigator Award. In March 2020 I was very happy to be awarded the Royal Statistical Society Research Prize.

Research

My research interests are mainly in developing statistical theory and methodology in nonparametric settings. Problems I have worked on include the estimation of entropy and other functionals, (conditional) independence testing and classification. I am also particularly interested in the application of nearest neighbour methods and permutation tests.

Core Statistical Publications and Preprints

  1. Berrett, T. B. and Samworth, R. J. (2022+) Optimal nonparametric testing of Missing Completely At Random, and its connections to compatibility. Preprint (.pdf). The accompanying R package MCARtest is available from CRAN.

  2. Li, M., Berrett, T. B. and Yu, Y. (2022+) On robustness and local differential privacy. Preprint (.pdf).

  3. Berrett, T. B. and Samworth, R. J. (2022+) Efficient two-sample functional estimation and the super-oracle phenomenon. Preprint (.pdf).

  4. Dubois, A., Berrett, T. B. and Butucea, C. (2022+) Goodness-of-fit testing for Hölder continuous densities under local differential privacy. Foundations of Modern Statistics - Festschrift in Honor of Vladimir Spokoiny, to appear (.pdf).

  5. Li, M., Berrett, T. B. and Yu, Y. (2022) Network change point localisation under local differential privacy. Advances in Neural Information Processing Systems 35 (NeurIPS) (.pdf).

  6. Berrett, T. B. (2022) Invited discussion of 'Multiscale Fisher's independence test for multivariate dependence'. Biometrika, 109(3), 589-592. (.pdf).

  7. Berrett, T. B. and Yu, Y. (2021) Locally private online change point detection. Advances in Neural Information Processing Systems 34 (NeurIPS) (.pdf).

  8. Berrett, T. B. and Samworth, R. J. (2021) USP: an independence test that improves on Pearson's chi-squared and the G-test. Proc. R. Soc. A, 477, 20210549 (.pdf). The accompanying R package USP is available from CRAN.

  9. Berrett, T. B., Györfi, L. and Walk, H. (2021) Strongly universally consistent nonparametric regression and classification with privatised data. Electron. J. Stat., 15, 2430-2453. (.pdf)

  10. Berrett, T. B., Kontoyiannis, I. and Samworth, R. J. (2021) Optimal rates for independence testing via U-statistic permutation tests. Ann. Statist., 49(5), 2457-2490. (.pdf). The supplementary material can be found here: (.pdf).

  11. Berrett, T. B. and Butucea, C. (2020) Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms. Advances in Neural Information Processing Systems 33 (NeurIPS), (Oral, top 5.5% of accepted papers) (.pdf).

  12. Berrett, T. B., Wang, Y., Barber, R. F. and Samworth, R. J. (2020) The conditional permutation test for independence while controlling for confounders. J. Roy. Statist. Soc., Ser B, 82(1), 175-197 (.pdf) (Among the top 10% most downloaded papers of those published between January 2018 and December 2019.)

  13. Cannings, T. I., Berrett, T. B. and Samworth, R. J. (2020) Local nearest neighbour classification with applications to semi-supervised learning. Ann. Statist., 48(3), 1789-1814. (.pdf). The online supplementary material is available here: (.pdf)

  14. Berrett, T. B. and Butucea, C. (2019) Classification under local differential privacy. Annales de l'ISUP, 63(2-3), 191-205, (.pdf).

  15. Berrett, T. B. and Samworth, R. J. (2019) Nonparametric independence testing via mutual information. Biometrika, 106(3), 547-566. (.pdf). The accompanying R package MCARtest is available from CRAN.

  16. Berrett, T. B., Samworth, R. J. and Yuan, M. (2019) Efficient multivariate entropy estimation via k-nearest neighbour distances. Ann. Statist., 47, 288-318.(.pdf). The online supplementary material is available here: (.pdf)

  17. Berrett, T. B. (2017) Modern k-nearest neighbour methods in entropy estimation, independence testing and classification. PhD Thesis (.pdf)

Other Publications

  1. Chowdhury, M., Tarkinm J., Albaghdadi, M., Evans, N., Le, E., Berrett, T. B., Sadat, U., Joshi, F., Warburton, E., Buscombe, J., Hayes, P., Dweck, M., Newby, D., Rudd J. H. F. and Coughlin P. MB ChB, MD, FRCS. (2019) Vascular Positron Emission Tomography and Restenosis in Symptomatic Peripheral Arterial Disease: A Prospective Clinical Study. JACC: Cardiovascular Imaging, June 2019, 3070.

  2. Tern, P., Kujawiak, I., Saha, P., Berrett, T. B., Chowdhury, M. and Coughlin, P. MB ChB, MD, FRCS. (2018) Site and Burden of Lower Limb Atherosclerosis Predicts Long-Term Mortality in a Cohort of Patients with Peripheral Arterial Disease. Eur. J. Vasc. Endovasc. Surg., 56, 849-856.

Workshop Organisation

Together with Nikolai Leonenko, Richard Lockhart, Richard Samworth and Yihong Wu I organised a workshop in Cambridge from 9-11 September 2019 on “Estimation of entropies and other functionals: Statistics meets information theory”. The final programme and booklet of abstracts can be found here.

Teaching

In Term 1 of 2020 and 2021 I lectured the Warwick Statistics module Multivariate Statistics.

In Michaelmas 2017 I lectured the Part III course Topics in Statistical Theory. Example sheet one is here, example sheet two is here and example sheet three is here. I have previously supervised Part IB Statistics, Part II Principles of Statistics, Part II Statistical Modelling and Part II Applied Probability.