Hi! My name is Miguel Biron-Lattes, and I’m a Postdoctoral Fellow at SFU Statistics and Actuarial Sciences, working with Donald Estep and Derek Bingham on uncertainty quantification in inverse problems. Currently developing fully Bayesian surface-based models for imaging underground resources via muon tomography through a collaboration with Ideon.
I obtained a PhD in Statistics from the Department of Statistics at UBC Vancouver, under the supervision of Alexandre Bouchard-Côté and Trevor Campbell. Previously, I was a financial stability analyst at the Superintendency of Banks and Financial Institutions of Chile (SBIF). Before that, I completed a masters degree in statistics at Columbia University. Prior to that, I worked as a financial engineering analyst at CLGroup Financial Services Consulting in Santiago. I obtained my B.Eng.Sc in Industrial Engineering from the University of Chile. For more information, take a look at my resume.
I am interested in mathematical, statistical and computational methods that help us understand and interact with complex phenomena in the real world. By leveraging these methods we can build models of these systems which we can later use to inform decision making and other relevant processes. To these end, I have recently focused my attention on Bayesian methodology, because it combines powerful and expressive models with the ability to quantify the uncertainty in them. Some specific research interest are
- Monte Carlo techniques for Bayesian calibration and inverse problems
- Design and analysis of MCMC algorithms
- Regenerative MCMC methods
- Tempering / annealing techniques
- Pseudo-marginal inference
Recent talks
- 2026-02-18, Ideon: Introduction to Parallel Tempering (slides)
- 2025-08-27, CANSSI Monte Carlo Workshop: Bayesian inference for block-cave mining monitoring via muon tomography (slides)
- 2025-07-18, ICML 2025 CODEML Workshop: Pigeons.jl: Distributed sampling from intractable distributions (slides)
Publications
Liu, T., Surjanovic, N., Biron-Lattes, M., Bouchard-Côté, A., & Campbell, T. (2025)
AutoStep: Locally adaptive involutive MCMC.
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267, 39624-39650.
[Paper] :: [arXiv] :: [NumPyro implementation]
Luu, S., Xu, Z., Surjanovic, N., Biron-Lattes, M., Campbell, T., & Bouchard-Côté, A. (2025)
Is Gibbs sampling faster than Hamiltonian Monte Carlo on GLMs?
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258, 2881-2889.
[Paper] :: [arXiv]
Thompson, W., […], Biron-Lattes, M., et al. (2025)
On the Orbit of the Binary Brown Dwarf Companion GL229 Ba and Bb.
The Astronomical Journal 169(4), 193.
[Paper] :: [arXiv]
Surjanovic, N., Biron-Lattes, M., Tiede, P., Syed, S., Campbell, T., & Bouchard-Côté, A. (2025). Pigeons.jl: Distributed sampling from intractable distributions. The Proceedings of the JuliaCon Conferences, 7(69), 139.
[Paper] :: [code] :: [arXiv] :: [slides]
Biron-Lattes, M., Surjanovic, N., Syed, S., Campbell, T., & Bouchard-Côté, A. (2024). autoMALA: Locally adaptive Metropolis-adjusted Langevin algorithm. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238, 4600-4608.
[Paper] :: [arXiv] :: [Pigeons implementation] :: [poster]
Biron-Lattes, M., Campbell, T., & Bouchard-Côté, A. (2024). Automatic Regenerative Simulation via Non-Reversible Simulated Tempering. Journal of the American Statistical Association, 120(549), 318–330.
[Paper] :: [arXiv] :: [code] :: [IRSA2023-slides]
Biron-Lattes, M., Bouchard-Côté, A., & Campbell, T. (2023). Pseudo-marginal inference for CTMCs on infinite spaces via monotonic likelihood approximations. Journal of Computational and Graphical Statistics, 32(2), 513-527.
[Paper] :: [arXiv] :: [IMS2022-slides] :: [ISBA2021-slides] :: [ISBA2021-video]
Biron, M., Córdova, F., & Lemus, A. (2019) Banks’ business model and credit supply in Chile: the role of a state-owned bank. BIS Working Paper No 800.
[Working paper]
Biron, M., & Bravo, C. On the discriminative power of credit scoring systems trained on independent samples. In Data Analysis, Machine Learning and Knowledge Discovery (pp. 247-254). Springer International Publishing.
[Book chapter]