Diego Marcondes

About me

I earned a BS in Statistics and a PhD in Applied Mathematics from the University of São Paulo, Brazil. My research interests in data science are at the intersection of probability theory, statistics, applied mathematics and computer science. In particular, I am interested in developing learning methods with a strong mathematical basis which do not only have a high performance, but are controllable and interpretable, with applications to scientific problems, and signal and image processing. I am currently working on operator learning based on mathematical morphology and physics-informed neural networks for solving forward and inverse problems.

I am a research fellow at the Mathematical Data Science Centre, Mathematical Sciences Institute, The Australian National University. Previously, I was a postdoc at the Computer Science Department, Institute of Mathematics and Statistics, University of São Paulo (2022-2024), and a visiting postdoctoral scholar at the Department of Electrical and Computer Engineering, Texas A&M University (2023-2024).

Google Scholar CV

Publications

Preprint

Marcondes, D. Complexity Dependent Error Rates for Physics-informed Statistical Learning via the Small-ball Method. ArXiv 2510.23149.

Marcondes, D., Braga-Neto, U. Generalized Resubstitution for Regression Error Estimation. ArXiv 2410.17948.

Marcondes, D.; Simonis, A. Metastable Financial Markets. ArXiv 2310.13081.

Marcondes, D.; Peixoto, C. Distribution-free Deviation Bounds and The Role of Domain Knowledge in Learning via Model Selection with Cross-validation Risk Estimation. ArXiv 2303.08777.

Articles Published in Peer-reviewed Journals

[13] Marcondes, D., Feldman, M., Barrera, J. Unrestricted Sequential Discrete Morphological Neural Networks. Journal of Mathematical Imaging and Vision. 2025.

[12] Peixoto, C.; Marcondes, D.; Melo, M. P.; Maia, A. C.; Correia, L. A. Prediction of healthcare costs on consumer direct health plan in the Brazilian context. Revista Brasileira de Economia. 2025.

[11] Marcondes, D.; Simonis, A.; Barrera, J. Back to basics to open the black box. Nature Machine Intelligence. 2024

[10] Marcondes, D.; Barrera, J. Discrete Morphological Neural Networks. SIAM Journal on Image Sciences. 2024

[9] Landim, C.; Marcondes, D.; Seo, I. A resolvent approach to metastability. Journal of the European Mathematical Society, pp.1-56. 2023

[8] Landim, C.; Marcondes, D.; Seo, I. Metastable behavior of weakly mixing Markov chains: The case of reversible, critical zero-range processes. Annals of Probability, 51 (1) 157 - 227. 2023

[7] Ferreira, C. P.; Marcondes, D.; Melo, M. P.; Oliva, S. M.; Peixoto, C.; Peixoto, P. S. A snapshot of a pandemic: the interplay between social isolation and COVID-19 dynamics in Brazil. Patterns, 2(10).

[6] Peixoto P. S.; Marcondes, D.; Peixoto, C.; Oliva S. M. Modeling future spread of infections via mobile geolocation data and population dynamics. An application to COVID-19 in Brazil. PLoS ONE 15(7): e0235732. 2020

[5] Marcondes, D.; Peixoto, C.; Stern, J. M. Assessing randomness in case assignment: the case study of the Brazilian Supreme Court, Law, Probability and Risk, Volume 18, Issue 2-3, Pages 97–114. 2019

[4] Marcondes, D.; Peixoto, C.; Maia, A. C. A Survey of a Hurdle Model for Heavy-Tailed Data Based on the Generalized Lambda Distribution. Communications in Statistics - Theory and Methods 49, no. 4, 781–808. 2020

[3] Marcondes, D.; Simonis, A.; Barrera, J. Feature Selection based on the Local Lift Dependence Scale. Entropy, 20, 97. 2018

[2] Marcondes, D.; Marcondes, N.R. A Nonparametric Statistical Approach to Content Analysis of Items. Stats, 1, 1-13. 2018

[1] Marcondes, D.; Peixoto, C.; Souza, K.; Wechsler, S. Entrance Fees and a Bayesian Approach to the St. Petersburg Paradox. Philosophies, 2, 11, 2017

Articles Published in Peer-reviewed Conference Proceedings

[4] Marcondes, D. On the representation of stack operators by mathematical morphology. ArXiv 2504.09766. To appear in proceedings of the 4th International Conference on Discrete Geometry and Mathematical Morphology (DGMM 2025).

[3] Marcondes, D., Barrera, J. The Lattice Overparametrization Paradigm for the Machine Learning of Lattice Operators. In: Brunetti, S., Frosini, A., Rinaldi, S. (eds) Discrete Geometry and Mathematical Morphology. DGMM 2024. Lecture Notes in Computer Science, vol 14605. Springer, Cham, 2024

[2] Marcondes, D., Feldman, M., Barrera, J. An Algorithm to Train Unrestricted Sequential Discrete Morphological Neural Networks. In: Brunetti, S., Frosini, A., Rinaldi, S. (eds) Discrete Geometry and Mathematical Morphology. DGMM 2024. Lecture Notes in Computer Science, vol 14605. Springer, Cham, 2024

[1] Marcondes, D.; Simonis A.; Barrera, J.. Feature selection from local lift dependence‑based partitions. In Bayesian Inference and Maximum Entropy Methods in Science and Engineering: MaxEnt 37, Jarinu, Brazil, July 09–14, 2017 37, pages 43– 53. Springer, 2018.

Unpublished

Marcondes, D.; Simonis, A.; Barrera, J. The role of prior information and computational power in Machine Learning. ArXiv 2211.01972. 2022

Marcondes, D. Parameter estimation in dynamical systems via Statistical Learning: a reinterpretation of Approximate Bayesian Computation applied to COVID-19 spread. ArXiv 2007.14229. 2021

Marcondes, D.; Simonis, A. Local Lift Dependence Scale. ArXiv 1901.10012. 2019

Marcondes, D.; Peixoto, C. Random Coin Tossing with unknown bias. ArXiv 1709.02362. 2017

Peixoto, C.; Marcondes, D. Stopping Times of Random Walks on a Hypercube. ArXiv 1709.02359. 2017

PhD Thesis

Marcondes, D.; A data-driven systematic, consistent and non-exhaustive approach to Model Selection. PhD Thesis in Applied Mathematics. University of São Paulo, Brazil. 2022.

Science Communication

Marcondes, D.; A Matemática no Combate à COVID-19, Noticiário Eletrônico da Sociedade Brasileira de Matemática, 19, Maio de 2020.

Teaching

University of São Paulo

MAP5005 - Introduction to Scientific Machine Learning (August, 2024 (Moodle))

The Australian National University

MATH1013 - Calculus (2/2025)

Special topics: Scientific Machine Learning (1/2025)

CONTACT

Mathematical Sciences Institute, The Australian National University

Room 1.48, Hanna Neumann Building 145

Email: diego.marcondes@anu.edu.au

Page updated

Google Sites

Report abuse