MSc Thesis, 2024
This is my MSc thesis, where I analysed a recent proof of the fact that a stationary, non-ergodic, quadratic and locally-optimal 2D Poisson matching does not exist.
Recommended citation: C. C. Perello, C. A. (2024), Non-existence of the 2D quadratic Poisson optimal matching.
Appeared in Stat, 2023
This paper is an extension of my 2nd year group project, which consisted on fitting Hawkes processes to the London Santander Cycle bike-sharing system. In this paper we employ a spatial component in the model to take in account distances between docking stations when predicting bike usage.
Recommended citation: F. Sanna Passino, Y. Che, C. C. Perello, C. A. (2023). Graph-based mutually exciting point processes for modelling event times in docked bike-sharing systems. https://arxiv.org/abs/2311.00595
Preprint (submitted for publication), 2023
This paper, which stemmed out of my BSc project, introduces a new adaptive importance sampling algorithm that used adaptive optimisation to adapt the proposal distribution.
Recommended citation: C. C. Perello, C. A., Akyildiz, Ö. D. (2023). Adaptively Optimised Adaptive Importance Samplers. https://arxiv.org/abs/2307.09341
Appeared in Bayesian Analysis, 2021
In this paper we fit beta splines to COVID-19 mortality data for each US state and use the fitted curves to estimate future deaths.
Recommended citation: Monod, M., Blenkinsop, A., Brizzi, A., Chen, Y., Perello, C. C. C., Jogarah, V., Wang, Y., Flaxman, S., Bhatt, S., & Ratmann, O. (2021). Regularised B-splines projected Gaussian Process priors to estimate time-trends of age-specific COVID-19 deaths related to vaccine roll-out. https://arxiv.org/abs/2106.12360