Pedro L. C. Rodrigues

Pedro L. C. Rodrigues

Research scientist at Inria

Publications

The following list of publications is first divided into research topics and then organized in chronological order. Topics are (click to jump directly):

You can also check my profile at Google scholar for a (probably) more updated list.

Works on simulation-based inference

These publications are related to the research topic that I started developping during my post-doc and is currently my main topic of interest.

  1. J Linhart, G V Cardoso, A Gramfort, S Le Corff, and PLC Rodrigues. “Diffusion posterior sampling for simulation-based inference in tall data settings ”. Under review. Paper available at arXiv:2404.07593.
  2. H Häggström, PLC Rodrigues, G Oudoumanessah, F Forbes, U Picchini. “Fast, accurate and lightweight sequential simulation-based inference using Gaussian locally linear mappings ”. Accepted by TMLR, July 2024. Paper available at arXiv:2403.07454.
  3. J Linhart, A Gramfort, PLC Rodrigues. “L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference ”. Accepted at NeurIPS 2023. Paper available at arXiv:2306.03580.
  4. N Tolley, PLC Rodrigues, A Gramfort, S Jones. “Methods and considerations for estimating parameters in biophysically detailed neural models with simulation based inference”. Under review. Paper available at bioRxiv:2023.04.17.537118v1.
  5. J Linhart, A Gramfort, PLC Rodrigues. “Validation Diagnostics for SBI algorithms based on Normalizing Flows”. Accepted at at the Workshop on Machine Learning and the Physical Sciences at NeurIPS 2022. Paper available at arXiv:2211.09602.
  6. PLC Rodrigues, Thomas Moreau, Gilles Louppe, A Gramfort. “HNPE: Leveraging Global Parameters for Neural Posterior Estimation ”. Accepted at NeurIPS 2021. Paper available at arXiv:2102.06477.
  7. PLC Rodrigues and A Gramfort. “Learning summary features of time series likelihood free inference”. Accepted at the Workshop on Machine Learning and the Physical Sciences at NeurIPS 2020. Paper available at arXiv:2012.02807 .
  8. M Jallais, PLC Rodrigues, A Gramfort, D Wassermann. “Cytoarchitecture measurements in brain gray matter using likelihood-free Inference”. Accepted at IPMI 2021. Paper available at hal-03090959.

Works on transfer learning

Both journal papers lay the mathematical foundations of my contributions in transfer learning for data defined in a SPD manifold. The other conference papers were all oral presentations, showing the growing interest of the research community in these methods.
  1. A Mellot, A Collas, PLC Rodrigues, D Engemann, A Gramfort. “Harmonizing and aligning M/EEG datasets with covariance-based techniques to enhance predictive regression modeling”. Neuroscience Imaging, 2023, pp.1-26. Paper available at hal-04328670
  2. L Bougrain, S Rimbert, PLC Rodrigues, G Canron, F Lotte. “Guidelines to use transfer learning for motor imagery detection: an experimental study”. Accepted at the IEEE NER2021 conference. December, 2020.
  3. PLC Rodrigues, M Congedo, C Jutten, “Dimensionality transcending: a method for merging BCI datasets with different dimensionalities” IEEE Transactions on Biomedical Engineering, July, 2020, in press. Paper available at hal-02905045. Related code available here.
  4. PLC Rodrigues, M Congedo, C Jutten. “‘When does it work?’: An exploratory analysis of transfer learning for BCI”. 8th Graz Brain-Computer Interface Conference 2019, September, 2019, Graz, Austria. Oral presentation. Best student paper award. Paper available at hal-02321580.
  5. PLC Rodrigues, M Congedo, C Jutten. “A data imputation method for matrices in the symmetric positive definite manifold”. XXVIIème colloque GRETSI (GRETSI 2019), August, 2019, Lille, France. Oral presentation. Paper available at hal-02321587.
  6. PLC Rodrigues, C Jutten, M Congedo, “Riemannian Procrustes analysis: transfer learning for brain-computer interfaces”. IEEE Transactions on Biomedical Engineering, vol. 66, no. 8, pp. 2390-2401, December, 2018. Paper available at hal-01971856. Related code available here.

Works on dimensionality reduction

These were the first published works of my Ph.D. thesis. They are based on the widely known mathematical framework of diffusion maps and extend it to the case of data points defined in the symmetric-positive definite manifold. Reference [8] is the first work in the literature, to the best of my knowledge, that applies these concepts to the analysis of multivariate time series.
  1. PLC Rodrigues, M Congedo, C Jutten. “Multivariate time-series analysis via manifold learning”. IEEE Statistical Signal Processing Workshop (SSP 2018), June, 2018, Fribourg-en-Brisgau, Germany. Paper available at hal-01868167. Related code available here.
  2. PLC Rodrigues, F Bouchard, M Congedo, C Jutten. “Dimensionality reduction for BCI classification using Riemannian geometry”. 7th Graz Brain-Computer Interface Conference. September, 2017, Graz, Austria. Oral presentation. Paper available at hal-01591258. Related code available here.
  3. F Bouchard, PLC Rodrigues, J Malick, M Congedo. “Réduction de dimension pour la séparation aveugle de sources”. XXVIème colloque GRETSI (GRETSI 2017), September, 2017. Juan-Les-Pins, France. Paper available at hal-01589766.
  4. PLC Rodrigues, F Bouchard, M Congedo, C Jutten. “Géométrie Riemannienne appliquée à la réduction de la dimension de signaux EEG pour les interfaces cerveau-machine”. XXVIème colloque GRETSI (GRETSI 2017), September 2017, Juan-Les-Pins, France. Oral presentation. Paper available at hal-01591252.
  5. M Congedo, PLC Rodrigues, F Bouchard, A Barachant, C Jutten. “A closed-form unsupervised geometry-aware dimensionality reduction method in the Riemannian manifold of SPD matrices”. 39th International Conference of the IEEE EMBS (EMBC), Jeju Island, South Korea, 2017, pp.3198-3201. Paper available at hal-01563153.

Works on neural connectivity estimation

These were my first published works containing the results of the research developped during my master of science in Brazil.
  1. PLC Rodrigues and LA Baccalá, “Statistically significant time-varying neural connectivity estimation using generalized partial directed coherence”. 2016 38th Annual International Conference of the IEEE EMBS (EMBC), Orlando, Florida, 2016, pp. 5493-5496. Finalist of the best student paper award. Oral presentation. Paper available here. Related code available here.
  2. PLC Rodrigues and LA Baccalá, “A new algorithm for neural connectivity estimation of EEG event related potentials”. 2015 37th Annual International Conference of the IEEE EMBS (EMBC), Milan, 2015, pp. 3787-3790. Oral presentation. Paper available here. Related code available here.