Rechercher
Menu
Je me connecte
Rechercher
  • Accueil
Photo of Estelle Massart

Estelle Massart

Professeure
estelle.massart@uclouvain.be

SST/EPL Ecole polytechnique de Louvain (EPL)

SST/ICTM Institute of Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM)

SST/ICTM/INMA Pôle en ingénierie mathématique (INMA)

2026
Article de journal

Taminiau, T., Nunes Grapiglia, G., & Massart, E. (2026). Enhancing finite-difference-based derivative-free optimization with machine learning. Optimization Letters, 20(6), 1159-1177. https://doi.org/10.1007/s11590-026-02281-1 (Original work published 2026)

https://research.dial.uclouvain.be/handle/2078.5/278604


Oswald, A., & Massart, E. (2026). Expressivity of congruence-based architectures for DNNs on positive-definite matrices. Submitted. (Original work published 2026)

https://research.dial.uclouvain.be/handle/2078.5/278616


Cartis, C., Liang, X., Massart, E., & Otemissov, A. (2026). Learning the subspace of variation for global optimization of functions with low effective dimension. SIAM Journal on Optimization. Submitted. (Original work published 2026)

https://research.dial.uclouvain.be/handle/2078.5/278620


Papier de conférence

Massion, B., Makhlouf, R., & Massart, E. (2026, May 29). The role of class encoding in neural collapse. EUSIPCO 2026, Bruges, Belgium.

https://research.dial.uclouvain.be/handle/2078.5/278617


Tansley, E., Massart, E., & Cartis, C. (2026, May 2). On the Neural Feature Ansatz for Deep Neural Networks. AISTATS 2026, Tangier, Marocco.

https://research.dial.uclouvain.be/handle/2078.5/278618


2025
Papier de conférence

Massion, B., & Massart, E. (2025). Grassmannian Frame Computation via Accelerated Alternating Projections. Proceedings of the International Conference on Sampling Theory and Applications. Published. Sampling Theory and Applications, Vienna. https://doi.org/10.1109/SampTA64769.2025.11133550 (Original work published 2025)

https://research.dial.uclouvain.be/handle/2078.5/262619


Rapport

Adel, T., Agarwal, A., Chrétien, S., Massart, E., Mokeev, D., Rungger, I., & Thompson, A. (2025). A Langevin sampler for quantum tomography.

https://research.dial.uclouvain.be/handle/2078.5/267829


2023
Papier de conférence

Massart, E., & Abrol, V. (2023). Coordinate descent on the Stiefel manifold for deep neural network training. ESANN 2023 proceedings. Published. 31st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning., Bruges, Belgium.

https://research.dial.uclouvain.be/handle/2078.5/253777


2022
Papier de conférence

Massart, E., & Abrol, V. (2022). Coordinate Descent on the Orthogonal Group for Recurrent Neural Network Training. Proceedings of the AAAI Conference on Artificial Intelligence, 36(7), 7744-7751. https://doi.org/10.1609/aaai.v36i7.20742 (Original work published 2022)

https://research.dial.uclouvain.be/handle/2078.5/253822


Massart, E. (2022). Improving weight clipping in Wasserstein GANs. Proceedings of the IEEE International Conference on Pattern Recognition (ICPR). Published. 2022 26th International Conference on Pattern Recognition (ICPR), Montreal, QC, Canada. https://doi.org/10.1109/icpr56361.2022.9956056

https://research.dial.uclouvain.be/handle/2078.5/224111


Massart, E. (2022). Orthogonal regularizers in deep learning: how to handle rectangular matrices? Proceedings of the IEEE International Conference on Pattern Recognition (ICPR). Published. 2022 26th International Conference on Pattern Recognition (ICPR), Montreal, QC, Canada. https://doi.org/10.1109/icpr56361.2022.9956205

https://research.dial.uclouvain.be/handle/2078.5/224317


Article de journal

Cartis, C., Massart, E., & Otemissov, A. (2022). Global optimization using random embeddings. Mathematical Programming, 200(2), 781-829. https://doi.org/10.1007/s10107-022-01871-y (Original work published 2022)

https://research.dial.uclouvain.be/handle/2078.5/253815


Cartis, C., Massart, E., & Otemissov, A. (2022). Bound-constrained global optimization of functions with low effective dimensionality using multiple random embeddings. Mathematical Programming, 198(1), 997-1058. https://doi.org/10.1007/s10107-022-01812-9 (Original work published 2022)

https://research.dial.uclouvain.be/handle/2078.5/253804


2021
Article de journal

Musolas, A., Massart, E., Hendrickx, J., Absil, P.-A., & Marzouk, Y. (2021). Low-rank multi-parametric covariance identification. Bit (Lisse) : numerical mathematics, 62, 221-249. https://doi.org/10.1007/s10543-021-00867-y (Original work published 2021)

https://research.dial.uclouvain.be/handle/2078.5/253781


2020
Article de journal

Massart, E., & Absil, P.-A. (2020). Quotient Geometry with Simple Geodesics for the Manifold of Fixed-Rank Positive-Semidefinite Matrices. SIAM Journal on Matrix Analysis and Applications, 41(1), 171-198. https://doi.org/10.1137/18m1231389 (Original work published 2020)

https://research.dial.uclouvain.be/handle/2078.5/92745


2019
Papier de conférence

Massart, E., Gousenbourger, P.-Y., Nguyen, T. S., Stykel, T., & Absil, P.-A. (2019). Interpolation on the manifold of fixed-rank positive-semidefinite matrices for parametric model order reduction: preliminary results. ESANN 2019 Proceedings, p. 281-286.

https://research.dial.uclouvain.be/handle/2078.5/226859


Nguyen, T. S., Gousenbourger, P.-Y., Massart, E., & Absil, P.-A. (2019). Online balanced truncation for linear time-varying systems using continuously differentiable interpolation on Grassmann manifold. 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), p. 165-170. https://doi.org/10.1109/codit.2019.8820675

https://research.dial.uclouvain.be/handle/2078.5/253847


Massart, E., Hendrickx, J., & Absil, P.-A. (2019). Curvature of the Manifold of Fixed-Rank Positive-Semidefinite Matrices Endowed with the Bures–Wasserstein Metric. Lecture Notes in Computer Science : Geometric Science of Information, p. 739-748. https://doi.org/10.1007/978-3-030-26980-7_77

https://research.dial.uclouvain.be/handle/2078.5/253727


Szczapa, B., Daoudi, M., Berretti, S., Del Bimbo, A., Pala, P., & Massart, E. (2019). Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Published. ICCV Human Behavior Understanding workshop, 2019, Seoul, Korea.

https://research.dial.uclouvain.be/handle/2078.5/224318


Thèse

Massart, E. (2019). Data fitting on positive-semidefinite matrix manifolds.

https://research.dial.uclouvain.be/handle/2078.5/124656


2018
Article de journal

Gousenbourger, P.-Y., Massart, E., & Absil, P.-A. (2018). Data Fitting on Manifolds with Composite Bézier-Like Curves and Blended Cubic Splines. Journal of Mathematical Imaging and Vision, 61(5), 645-671. https://doi.org/10.1007/s10851-018-0865-2 (Original work published 2018)

https://research.dial.uclouvain.be/handle/2078.5/254223


2017
Article de journal

Massart, E., Hendrickx, J., & Absil, P.-A. (2017). Matrix geometric means based on shuffled inductive sequences. Linear Algebra and Its Applications, 252, 334-359. https://doi.org/10.1016/j.laa.2017.05.036 (Original work published 2018)

https://research.dial.uclouvain.be/handle/2078.5/254715


Papier de conférence

Massart, E., & Chevallier, S. (2017). Inductive Means and Sequences Applied to Online Classification of EEG. Lecture Notes in Computer Science : Geometric Science of Information, p. 763-770. https://doi.org/10.1007/978-3-319-68445-1_88

https://research.dial.uclouvain.be/handle/2078.5/254772


Gousenbourger, P.-Y., Massart, E., Musolas, A., Absil, P.-A., Hendrickx, J., Jacques, L., & Marzouk, Y. (2017). Piecewise-Bezier C1 smoothing on manifolds with application to wind field estimation. 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2017), 305-3010.

https://research.dial.uclouvain.be/handle/2078.5/254227


2016
Papier de conférence

Massart, E., Hendrickx, J., & Absil, P.-A. (2016). Extending a two-variable mean to a multi-variable mean. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium.

https://research.dial.uclouvain.be/handle/2078.5/227106


Unités d'enseignement pour 2026

Libellé Code
Algèbre LEPL1101
Projet 4 (en mathématiques appliquées) LEPL1507
Algorithmique numérique LINFO1113
Nonlinear dynamical systems LINMA2361
High-Dimensional Data Analysis and Optimization LINMA2474
Statistiques et sciences des données LSINC1109
Algorithmique numérique LSINC1313