Research interests

My main research interests lie within mathematical statistics and include nonparametric inference, frequentist guarantees of Bayesian methods, statistical inverse problems (especially discretely observed stochastic processes) and empirical process theory.

I am also interested in and have briefly worked on exit problems for Lévy processes, completion of Bayesian networks and differential equations (their connections with probability and existence and uniqueness topics).

Publications

  • Efficient nonparametric inference for discretely observed compound Poisson processes [ArXiv, doi]. Probability Theory and Related Fields 170 (2018), 475-523.

    doi: 10.1007/s00440-017-0761-5. Matlab code available on request.

Preprints

  • Adaptive nonparametric estimation of compound Poisson processes robust to the discrete-observation scheme [ArXiv]. In review.

Unpublished research

  • Efficient nonparametric inference for discretely observed compound Poisson processes [doi]. PhD thesis (2017). doi: 10.17863/CAM.8528. Matlab code available on request.
  • The two-sided exit problem for Lévy processes [.pdf]. CCA research project (2012).
  • Gradient-based optimisation method [.pdf]. CCA research project (2012). Matlab code available on request.
  • On the use of Bayesian networks to model stress events in banking [.pdf]. MSc thesis (2011). Partly published in “Denev, A. and Rebonato, R., 2014. Portfolio Management under Stress: A Bayesian-Net Approach to Coherent Asset Allocation. Cambridge University Press, Cambridge” [Amazon].
Advertisements