Scholar
Petros Dellaportas
Google Scholar ID: E0FmV8AAAAAJ
University College London and Athens University of Economics and Business
Citations & Impact
Citations
1,125
H-index
19
i10-index
33
Publications
20
Co-authors
28
list available
Contact
Publications
Resume (English only)
Academic Achievements
- 2024: Co-authored 'Learning variational autoencoders via MCMC speed measures' with Marcel Hirt and Vasileios Kreouzis, published in Statistics and Computing
- 2023: Co-authored 'Bayesian Tensor Factorisations for Time Series of Counts' with Zhongzhen Wang and Ioannis Kosmidis, published in Machine Learning
- 2023: Co-authored 'Reservoir computing for macroeconomic forecasting with mixed frequency data', published in International Journal of Forecasting
- 2023: Co-authored 'Bayesian online change point detection with Hilbert space approximate Student-t process' with Jeremy Sellier, published in ICML 2023
- 2023: Co-authored 'Doubly-online changepoint detection for monitoring health status during sports activities' with Mattia Stival and Mauro Bernardi, published in Annals of Applied Statistics
- 2023: Co-authored 'Flexible marked spatio-temporal point processes with applications to event sequences from association football' with Santhosh Narayanan and Ioannis Kosmidis, published in Journal of the Royal Statistical Society Series C
- 2023: Co-authored 'Inference for partially observed Riemannian Ornstein-Uhlenbeck diffusions of covariance matrices' with Mai Ngoc Bui and Yvo Pokern, published in Bernoulli
- 2023: Co-authored 'Missing data patterns in runners’ careers: do they matter?' published in Journal of the Royal Statistical Society Series C
- 2023: Co-authored 'Scalable and Interpretable Marked Point Processes' with Aristeidis Panos and Ioannis Kosmidis, published in AISTATS 2023
- 2023: Co-authored 'Sparse Spectral Bayesian Permanental Process with Generalized Kernel' with Jeremy Sellier, published in AISTATS 2023
Research Experience
- Involved in multiple research projects, including:
- Dynamic pricing
- Poisson processes for identity systems and cyber security
- Reservoir Computing for Macroeconomic Modelling
- Detecting anomalies in the VAT network (identifying abnormal data events and fraudulent behavior)
- Forecasting with large macroeconomic and financial datasets
- Probabilistic fault detection and power forecasting in wind parks using SCADA data from wind turbines
- Recovering utilities from observational data (inverse reinforcement learning in consumer behavior modeling)
