I am an Assistant Professor (Maître de Conférences) at the Department of Mathematics of Université Paris-Saclay. I am also a member of the Inria Celeste team.
Before that, I was a postdoctoral researcher at EPFL in BAN chair. I did my PhD at Inria Paris under the supervision of Laurent Massoulié and Marc Lelarge.
Here is a short CV.
Email adress: luca [dot] ganassali [at] universite-paris-saclay [dot] fr
Physical adress: Bâtiment 307, rue Michel Magat, Faculté des Sciences d’Orsay, Université Paris-Saclay, 91400 Orsay
I am currently working on:
- Algorithmic fairness and causality
- Optimal transport for statistical learning
- Statistical inference in graphs and matrices
- Informational and computational thresholds for algorithms on random instances
- September 2025: a new preprint is out! Together with Lucas De Lara, we investigate the connections between statistical transport maps and causal inference. Our work compares three notions of multivariate monotone transport—cyclically monotone, quantile-preserving, and triangular monotone maps—deriving conditions for their equivalence and clarifying their structural properties. We then show how counterfactual reasoning in structural causal models can be formulated as a problem of selecting transport maps, highlighting when causal assumptions align with classical statistical transports. 👉 see the preprint
- I am looking for a PhD student! Together with Evgenii Chzhen, we have a PhD offer at the interface between mathematical statistics and machine learning, namely about Handling unfairness in data: modelling, detecting, and debiasing. Have a look at the PhD proposal. Students are encouraged to apply by email.
- I recently gave an introductionary talk at IHES about Unsupervised Alignment of Graphs and Embeddings: Fundamental Limits and Computational Methods. [Youtube link].
L. De Lara, L. Ganassali. What is a good matching of probability measures? A counterfactual lens on transport maps, 2025, submitted.
[arXiv]
M. Even, L. Ganassali, J. Maier, L. Massoulié. Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem, 2024, NeurIPS 2024.
[NeurIPS presentation] [arXiv]
F. Jamshidi, L. Ganassali, N. Kiyavash. On sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery, 2023, ICML 2024.
[PMLR] [arXiv]
S. Akbari, L. Ganassali, N. Kiyavash. Learning causal graphs via monotone triangular transport maps, 2023, NeurIPS 2023 Workshop on Optimal Transport and Machine Learning.
[arXiv]
L. Ganassali, L. Massoulié, G. Semerjian. Statistical limits of correlation detection in trees, 2022, Annals of Applied Probability.
[journal] [arXiv]
L. Ganassali. The graph alignment problem: fundamental limits and efficient algorithms, PhD dissertation, 2022.
[pdf] [arXiv]
L. Ganassali, M. Lelarge, L. Massoulié. Correlation detection in trees for partial graph alignment, 2021, Annals of Applied Probability (short version: ITCS 2022).
[journal] [ITCS (extended abstract)] [arXiv]
L. Ganassali, M. Lelarge, L. Massoulié. Impossibility of Partial Recovery in the Graph Alignment Problem, 2021, COLT 2021.
[PMLR] [COLT presentation] [arXiv]
L. Ganassali. Sharp threshold for alignment of graph databases with Gaussian weights, 2020, Mathematical and Scientific Machine Learning (MSML21).
[PMLR] [MSML presentation] [arXiv]
M. Akian, L. Ganassali, S. Gaubert, L. Massoulié. Probabilistic and mean-field model of COVID-19 epidemics with user mobility and contact tracing, 2020, preprint.
[arXiv]
L. Ganassali, L. Massoulié. From tree matching to sparse graph alignment, 2020, COLT 2020.
[PMLR] [COLT presentation] [arXiv]
L. Ganassali, M. Lelarge, L. Massoulié. Spectral alignment of correlated Gaussian random matrices, 2019, Advances in Applied Probability.
[journal]
[arXiv]
2025-2026. Statistiques (STA1), ENSTA, M1 MathsAppli, Université Paris-Saclay. Voir les slides et TDs.
2025-2026. Introduction à la modélisation statistique, M1 Maths&IA, Université Paris-Saclay.