Skip to main content

Valerio Perrone

I am a final year PhD student at the Oxford-Warwick Statistics Programme (OxWaSP), working under the joint supervision of Professor Yee Whye Teh (Oxford), Dr. Dario Spanò (Warwick) and Dr. Paul Jenkins (Warwick). I am also part of the Oxford statistical machine learning group (OxCSML).

My research interests lie in the fields of Bayesian machine learning and deep learning. In particular, I am interested in developing algorithms for large-scale machine learning and Bayesian models with realistic dependency structures. I have applied my work to Bayesian optimization, topic modelling, and population genetics.


  • V. Perrone, R. Jenatton, M. Seeger, C. Archambeau. Scalable Hyperparameter Transfer Learning. To appear in Neural Information Processing Systems (NIPS). 2018. [pdf] [arXiv] [workshop link]
  • J. Chan, V. Perrone, J. Spence, P. A. Jenkins, S. Mathieson and Yun S. Song. A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks. To appear in Neural Information Processing Systems (NIPS). 2018. Selected as Spotlight. [arXiv] [bioRxiv] [workshop link] [code]
  • V. Perrone, P. A. Jenkins, D. Spano, Y. W. Teh. Poisson Random Fields for Dynamic Feature Models. Journal of Machine Learning Research (JMLR). 2017. [pdf] [arXiv] [data] [video]
  • X. Lu*, V. Perrone*, L. Hasenclever, Y. W. Teh, S. J. Vollmer (*joint first author). Relativistic Monte Carlo. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS). 2017. [pdf] [arXiv] [code] [video]

Selected Talks & Posters


  • Term 2, 2017: Stochastic Processes (ST202)
  • Term 2, 2016: Probability Theory (ST318)
  • Term 1, 2015: Mathematical Statistics Part A (ST218)



  • v dot perrone at warwick dot ac dot uk
  • perrone at stats dot ox dot ac dot uk

Personal website

Google Scholar


Office No. D0.06
Department of Statistics
University of Warwick
CV4 7AL, Coventry (UK)