Oliver Orejola  

cv   scholar   github   linkedin   publications


I am a researcher with an affinity for physics, computer science and mathematics. I enjoy building things and solving problems. As an undergraduate at Univeristy of Colorado, I studied adiabatic quantum computation and category theory. My Ph.D. thesis at Tulane focused on time-series analysis and machine learning in a high-dimensional setting. My overarching interest revolves around tackling problems within the domain deep learning and explainable AI.



a few of my interests
random matrix theory         time series analysis         graph theory
machine learning         mult-agent LLMs         RAG systems
skateboarding         music         cooking


publications

On the empirical spectral distribution of large wavelet random matrices based on mixed-Gaussian fractional measurements in moderately high dimensions
Orejola, O., Didier, G., Wendt, H. and Abry, P.
submitted: arXiv preprint (2024)
Identifying high-dimensional self-similarity based on spectral clustering applied to large wavelet random matrices
Orejola, O., Didier, G., Wendt, H., and Abry, P.
to appear in 32th European Signal Processing Conference (EUSIPCO) (2024)
Bootstrap based test for the unimodality of estimated Hurst exponents. Performance assessment in high-dimensional analysis setting
Lucas, C.G., Wendt, H., Abry, P.,Didier, G., and Orejola, O.,
XXIXème Colloque Francophone de Traitement du Signal et des Images (GRETSI) (2023)
Shhh! The Logic of Clandestine Operations
Naumov, P., Oliver, O.
32nd International Joint Conference on Artificial Intelligence (IJCAI) (2023)
Hurst multimodality detection based on large wavelet random matrices
Didier, G., Orejola, O., Wendt, H., and Abry, P.
30th European Signal Processing Conference (EUSIPCO) (2022)