Welcome to my personal webpage!
Since October 2022, I am a postdoctoral researcher at EPFL in BAN chair led by Prof. Negar Kiyavash. Prior to that, I was a PhD student at Inria Paris in the Dyogene team, which is a joint team between Inria and ENS Paris, under the supervision of Laurent Massoulié and Marc Lelarge. Here is a short CV.
My research interests lie mainly within statistics, probability theory, graph theory and machine learning. I am interested in studying procedures for learning tasks and inference problems with geometry, symmetries or invariance. More specifically, I've been looking at inference problems in graphs and matrices, such as graph alignment, investigating the information-theoretical and computational thresholds, as well as designing and analyzing new algorithms on random instances to give a better understanding of the regimes in which they may suceed.
Other current topics I'm interested in are graph neural networks, statistical learning with optimal transport, and causality.
Email adress: luca [dot] ganassali [at] epfl [dot] ch
Physical adress: Office 316, Building ODY, EPFL, Lausanne.
L. Ganassali, L. Massoulié, G. Semerjian. Statistical limits of correlation detection in trees, 2022, submitted.
[arXiv]
L. Ganassali. The graph alignment problem: fundamental limits and efficient algorithms, PhD dissertation, 2022. [pdf]
L. Ganassali, M. Lelarge, L. Massoulié. Correlation detection in trees for partial graph alignment, 2021, Innovations in Theoretical Computer Science (ITCS 2022).
[arXiv] [ITCS (extended abstract)]
L. Ganassali, M. Lelarge, L. Massoulié. Impossibility of Partial Recovery in the Graph Alignment Problem, 2021, in Proceedings of Thirty Fourth Conference on Learning Theory (COLT 2021).
[arXiv] [PMLR] [COLT presentation]
L. Ganassali. Sharp threshold for alignment of graph databases with Gaussian weights, 2020, Mathematical and Scientific Machine Learning (MSML21).
[arXiv] [PMLR] [MSML presentation]
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, in Proceedings of Thirty Third Conference on Learning Theory (COLT 2020).
[arXiv] [PMLR] [COLT presentation]
L. Ganassali, M. Lelarge, L. Massoulié. Spectral alignment of correlated Gaussian random matrices, 2019, in Advances in Applied Probability.
[arXiv] [journal]
Upcoming: Young European Probabilists (YEP) workshop, Eindhoven, Mar. 27-31, 2023.
Upcoming: Séminaire de Probabilités/Statistiques, Institut de mathématique d'Orsay, Orsay, Jan. 12, 2023.
Séminaire de Probabilités, Centre de Mathématiques et Informatique, Université d'Aix-Marseille, Marseille, Nov. 15, 2022. (talk)
Theoretical Computer Science Spring School: Machine Learning, CIRM, Luminy, May 23-27, 2022.
CDM Seminar, EPFL, Mar. 17, 2022. (talk)
DACO Seminar, ETH Zürich, Feb. 28-Mar. 1, 2022. (talk)
Innovations in Theoretical Computer Science (ITCS), Berkeley (remote), Jan. 31-Feb. 3, 2022. (talk)
Stochastics Seminar, Georgia Tech (remote), Dec. 9, 2021. (talk)
Prairie Workshop, Paris, Nov. 10, 2021. (poster)
Colloque Jeunes Probabilistes et Statisticien-ne-s, Saint Pierre D'Oléron, Oct. 24-29, 2021. (talk, slides)
Workshop On Future Synergies for Stochastic and Learning Algorithms, CIRM, Luminy, Sept. 27-Oct. 1, 2021. (poster)
Junior conference Random networks and interacting particle systems (remote), Sept. 6-10, 2021. (talk)
Conference on Learning Theory (COLT) (remote), Aug. 15-19, 2021. (talk, slides, poster)
Mathematical and Scientific Machine Learning (MSML) (remote), Aug. 16-19, 2021. (talk)
Conference on Learning Theory (COLT) (remote), Jul. 9-12, 2020. (talk)
Workshop Spectra, Algorithms and Random Walks on Random Networks, CIRM, Luminy, Jan. 13-17, 2020.
Networking days, Orsay, Oct. 23, 2019. (talk)
Conferences: ISIT 2021, COLT 2022, MSML 2022.
Journals: Journal of Machine Learning Research, Annals of Statistics.
Spring 2020: Tutoring for the MAP361 course at Ecole Polytechnique, some revision exercices (in french) about
Borel-Cantelli lemma, Convergence of random variables,
and Estimation and CLT.
Spring 2021: TA for the MA16Y020 course: Statistiques et simulations probabilistes, L3, Université de Paris.
Spring 2021: TA for the MA1BY020 course: Statistiques, M1, Université de Paris.
Fall 2021: TA for the MT15Y030 course: Probabilités, L3, Université de Paris. Vous trouverez ici des exercices supplémentaires.
Spring 2022: TA for the MA1BY020 course: Statistiques, M1, Université de Paris. Voir les TPs.