I am a ProbAI Hub Postdoctoral research fellow in the Department of Statistics at the University of Warwick. I am broadly interested in probability, computational statistics, and optimization. In particular, my recent work focuses on connections between stochastic algorithms, optimal transport, gradient flows, and functional inequalities.

I obtained my PhD in Statistics at the University of Warwick, under the supervision of Adam M. Johansen and Andi Q. Wang.

*NEWS* : I am co-organizing the ProbAI Theory of Scaling Laws Workshop at the University of Warwick in Summer 2026. Link

Research

Research articles:

  • R. Caprio, A. Corenflos, S. Power. Wasserstein Contraction of Coordinate Ascent Variational Inference. arXiv 2605.30253. [arXiv]
  • R. Caprio, A.M. Johansen. Fast convergence of the Expectation Maximization algorithm under a logarithmic Sobolev inequality. Biometrika, 112(4), 2025. [journal][arXiv]
  • R. Caprio, J. Kuntz, S. Power, A.M. Johansen. Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities. Journal of Machine Learning Research, 26(103):1−38, 2025. [journal][arXiv]
  • R. Caprio, S. Power, A.Q. Wang. Analysis of Multiple-try Metropolis via Poincaré inequalities. Electronic Journal of Statistics, 20 (1), 915-941, 2026. [journal][arXiv]
  • R. Caprio, A.M. Johansen. A calculus for Markov chain Monte Carlo: studying approximations in algorithms. arXiv 2310.03853. [arXiv]

Thesis:

  • R. Caprio. Optimisation on Hybrid Spaces and its Application to Statistical Inference. PhD Thesis, University of Warwick. [link]

Discussions:

  • R. Caprio and A.M. Johansen’s contribution to the discussion of “Statistical Exploration of the Manifold Hypothesis” by Whiteley, Gray and Rubin-Delanchy, Journal of the Royal Statistical Society B: Statistical Methodology, 88 (2), 404-406, 2026.

Teaching