I am Giacomo Greco. As of September 2024 I am a PostDoc in Prof. Domenico Marinucci's group at University of Rome Tor Vergata. I will be working on Random Fields and their interplay with machine learning. My position is cofunded by the PRIN project GRAFIA and MUR Departement of Excellence Programme 2023-2027 MatMod@Tov.
Previously
I was a doctoral candidate at Eindhoven University of Technology, in Prof. dr. Mark A. Peletier's group. My supervisors were Prof. Alberto Chiarini (Univeristy of Padova) and Prof. Giovanni Conforti (Univeristy of Padova and CMAP, École Polytechnique).
01/09/2024 - Present
University of Rome Tor Vergata
01/09/2020 - 31/08/2024
Thesis defended on the 23/05/2024
Eindhoven University of Technology (TU/e)
03/01/2023 - 03/04/2023
École Polytechnique - IP Paris
07/10/2018 - 24/07/2020
Sapienza University of Rome
01/10/2015 - 24/07/2018
Sapienza University of Rome
"Considerate la vostra semenza:
fatti non foste a viver come bruti
ma per seguir virtute e canoscenza."
(last update: 05/05/2026)
I am interested in probability theory, in its interplay with analysis and geometry and in problems arising from AI and ML. Particularly I am interested in:
the Schrödinger Bridge Problem (SP) and its relationship with (Entropic) Optimal Transport,
Optimal Transport point of view in (Diffusion) Generative Modelling,
Random Fields and their relation with ML/GenAI,
stochastic optimal control problems: long-time behaviour and exponential ergodicity,
high-dimensional probability.
G. Greco, D. Marinucci.
Sparsity for isotropic spherical random fields
arXiv:2601.21535 (01/2026) - Accepted in a special issue of Theory of Probability and Mathematical Statistics
G. Greco.
A Malliavin-Gamma calculus approach to Score Based Diffusion Generative models for random fields
arXiv:2505.13189 (05/2025) - Accepted in INDAM-Springer volume Analysis and Geometry of Random Fields
G. Greco, L. Tamanini.
Hessian stability and convergence rates for entropic and Sinkhorn potentials via semiconcavity
Bernoulli 32(3): 2351-2378 (August 2026).
A. Chiarini, G. Conforti, G. Greco, L. Tamanini.
A semiconcavity approach to stability of entropic plans and exponential convergence of Sinkhorn's algorithm
arXiv:2412.09235 (12/2024)
G. Conforti, A. Durmus, G. Greco.
Quantitative contraction rates for Sinkhorn's algorithm: beyond bounded costs and compact marginals
arXiv:2304.04451 (04/2023) - Accepted in Annals of Applied Probability
G. Greco, M. Noble, G. Conforti, A. Durmus.
Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach
Proceedings of Thirty Sixth Conference on Learning Theory (COLT 2023) in PMLR 195:716-746 (2023)
A. Chiarini, G. Conforti, G. Greco, L. Tamanini.
Gradient estimates for the Schrödinger potentials: convergence to the Brenier map and quantitative stability
Communications in Partial Differential Equations 48:6, 895-943 (2023)
A. Chiarini, G. Conforti, G. Greco, Z. Ren.
Entropic turnpike estimates for the kinetic Schrödinger problem
Electron. J. Probab. 27: 1-32 (2022)
PhD thesis: The Schrödinger problem: where analysis meets stochastics.
Supervisors: Prof. Mark A. Peletier (TU/e), Prof. Alberto Chiarini (UniPD) and Prof. Giovanni Conforti (UniPD and IP Paris) - 05/2024
MSc thesis: Signal-to-noise ratio thresholds in principal component analysis.
Supervisor: Professor Alessandra Faggionato - 07/2020
BSc thesis: Homological algebra of unbounded complexes (in italian).
Supervisor: Professor Marco Manetti - 07/2018