Shakeel Gavioli-Akilagun

Hello! Welcome to Shakeel's academic website. I am a Fellow in the Department of Decision Analytics and Operations at City University Hong Kong, and a visiting Fellow by courtesy in the Department of Statistics at the London School of Economics. Previously I was a PhD student at the London School of Economics, where I was supervised by Professor Piotr Fryzlewicz. Some of my research interests include:
  • Multi-scale statistical modeling
  • Change points and feature detection
  • Shape constrained estimation
  • Kernel methods
A recent version of my CV can be found here.


Publications:

Fast and Optimal Inference for Change Points in Piecewise Polynomials via Differencing. S. Gavioli-Akilagun and P. Fryzlewicz. Electronic Journal of Statistics, 2025 [open access link; R package; numerical examples]

Invited discussion of "Automatic Change-Point Detection in Time Series via Deep Learning" by Li, Fearnhead, Fryzlewicz, and Wang. S. Gavioli-Akilagun. Journal of the Royal Statistical Society Series B, 2023 [discussion; slides; original paper]


Preprints and projects:

Optimal Online Change Detection via Random Fourier Features. F. Kalinke and S. Gavioli-Akilagun. In submission, 2025 [arXiv; software; numerical examples]

Adaptive Detection of Machine-Generated Text. H. Zhou, J. Zhu, P. Su, K. Ye, Y. Yang, S. Gavioli-Akilagun, and C. Shi. In submission, 2025

Causal Change Point Detection using Kernels. F. Quinzan and S. Gavioli-Akilagun Work in progress, 2025+

Detecting Changes in Production Frontiers. S. Gavioli-Akilagun, Y. Chen, and F. Ziegelmann. Work in progress, 2024+

Online Detection of Changes in Mean Reverting Processes with Local Cointergration. S. Gavioli-Akilagun, B. Dou, S. Tiwari, and Q. Yao. Work in progress, 2024+

Robust Inference for Change Points in Piecewise Polynomials using Confidence Sets. S. Gavioli-Akilagun and P. Fryzlewicz. Manuscript in preparation, 2023+


Recent and upcoming events:


Teaching:

This academic year (2025/26) I am the lecturer for the following courses: