I am an Assistant Professor (Maître de Conférences) at the Department of Mathematics of Université Paris-Saclay. 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.
I am currently working on:
- Statistical inference in graphs and matrices
- Informational and computational thresholds for algorithms on random instances
- Optimal transport for statistical learning
- Bayesian networks, causality and fairness
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
- December 4th-5th 2024: I will be participating to NeurIPS@Paris 2024. I'll be presenting our recent work (joint with Mathieu, Jakob and Laurent), Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem. Check out the paper here!
- I recently gave an introductionary talk at IHES about Unsupervised Alignment of Graphs and Embeddings: Fundamental Limits and Computational Methods. [Youtube link].
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.
[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]