Matías Altamirano

I’m a PhD Student in Statistical Science at UCL and part of the Fundamentals of Statistical Machine Learning research group supervised by Jeremias Knoblauch and François-Xavier Briol. My research focuses on robust Bayesian methods in time series models.

My PhD is supported by the Bloomberg Data Science PhD fellowship

Prior to starting my PhD, I worked as a research engineer at Center of Mathematical Modeling - Universidad de Chile, using data science and stochastic modeling to different projects.

News

Feb 11, 2025	💬 I’m co-organising the Post-Bayes Seminar Series, starting on 11/02!
Dec 9, 2024	🎉 I’m very happy to announce that I have been awarded the Bloomberg Data Science Ph.D. Fellowship!!
May 1, 2024	🎉 Our paper Outlier-robust Kalman Filtering through Generalised Bayes was accepted at ICML 2024.
May 1, 2024	🎉 Our paper Robust and Conjugate Gaussian Process Regression was accepted as a spotlight paper (top 3.5%) at ICML 2024.
Mar 24, 2024	💬 Presenting a poster at the Workshop on Functional Inference and Machine Intelligence at University of Bristol.

Selected Publications

Preprint

Robust and Conjugate Spatio-Temporal Gaussian Processes

William Laplante, Matias Altamirano, Andrew Duncan, and 2 more authors

arXiv preprint arXiv:2502.02450, 2025

arXiv Bib Code

@article{laplante2025robust,
  title = {Robust and Conjugate Spatio-Temporal Gaussian Processes},
  author = {Laplante, William and Altamirano, Matias and Duncan, Andrew and Knoblauch, Jeremias and Briol, Fran{\c{c}}ois-Xavier},
  journal = {arXiv preprint arXiv:2502.02450},
  year = {2025},
}

ICML

Outlier-robust Kalman Filtering through Generalised Bayes

Gerardo Durán-Martı́n, Matias Altamirano, Alexander Y Briol, and 5 more authors

In International Conference on Machine Learning, 2024

arXiv Bib Code

@inproceedings{duran2024outlier,
  title = {Outlier-robust Kalman Filtering through Generalised Bayes},
  author = {Dur{\'a}n-Mart{\'\i}n, Gerardo and Altamirano, Matias and Briol, Shestopaloff, Alexander Y and S\'anchez-Betancourt, Leandro and Knoblauch, Jeremias and Jones, Matt and Fran{\c{c}}ois-Xavier and Murphy, Kevin},
  booktitle = {International Conference on Machine Learning},
  year = {2024},
}

ICML

Robust and Conjugate Gaussian Process Regression

Matias Altamirano, François-Xavier Briol, and Jeremias Knoblauch

In International Conference on Machine Learning, 2024

arXiv Bib Code

@inproceedings{altamirano2024robustGP,
  title = {Robust and Conjugate Gaussian Process Regression},
  author = {Altamirano, Matias and Briol, Fran{\c{c}}ois-Xavier and Knoblauch, Jeremias},
  booktitle = {International Conference on Machine Learning},
  year = {2024},
}

ICML

Robust and Scalable Bayesian Online Changepoint Detection

Matias Altamirano, François-Xavier Briol, and Jeremias Knoblauch

In International Conference on Machine Learning, 2023

arXiv Bib Code

@inproceedings{altamirano2023robust,
  title = {Robust and Scalable {B}ayesian Online Changepoint Detection},
  author = {Altamirano, Matias and Briol, Fran{\c{c}}ois-Xavier and Knoblauch, Jeremias},
  booktitle = {International Conference on Machine Learning},
  year = {2023},
}

AISTATS

Nonstationary multi-output Gaussian processes via harmonizable spectral mixtures

Matias Altamirano, and Felipe Tobar

In International Conference on Artificial Intelligence and Statistics, 2022

Bib

@inproceedings{altamirano2022nonstationary,
  title = { Nonstationary multi-output {G}aussian processes via harmonizable spectral mixtures },
  author = {Altamirano, Matias and Tobar, Felipe},
  booktitle = {International Conference on Artificial Intelligence and Statistics},
  pages = {3204--3218},
  year = {2022},
}