Ludovico Theo Giorgini

About Me

I am an applied mathematician who leverages a broad spectrum of techniques—from generative AI and machine learning to stochastic modeling—to tackle complex data challenges in dynamical systems, ranging from one-dimensional chaotic maps to high-dimensional geophysical flows.

Publications

• L.T. Giorgini, T. Bischoff, A. Souza, KGMM: A K-means Clustering Approach to Gaussian Mixture Modeling for Score Function Estimation, arXiv (2025).
• L.T. Giorgini, A. Souza, D. Lippolis, P. Cvitanović and P. Schmid, Learning dissipation and instability fields from chaotic dynamics, arXiv (2025).
• L.T. Giorgini, W. Moon, and J.S. Wettlaufer, Analytical Survival Analysis of the Non-autonomous Ornstein-Uhlenbeck Process, J. Stat. Phys., 191, 138 (2024).
• L.T. Giorgini, K. Deck, T. Bischoff, A. Souza, Response Theory via Generative Score Modeling, Phys. Rev. Lett., 133, 267302 (2024).
• L.T. Giorgini, A. Souza and P. Schmid, Reduced Markovian Models of Dynamical Systems, Physica D: Nonlinear Phenomena, 470, 134393 (2024).
• L.T. Giorgini et al., Instantons in ϕ⁴ Theories: Transseries, Virial Theorems and Numerical Aspects, Phys. Rev. D, 110, 036003 (2024) (Editor's choice).
• U.D. Jentschura, L.T. Giorgini, Enhanced One-Step Neville Algorithm with Access to the Convergence Rate, Comp. Phys. Comm. (2024).
• N. Keyes, L.T. Giorgini and J.S. Wettlaufer, Stochastic Paleoclimatology: Modeling the EPICA Ice Core Climate Records, Chaos, 30, 093132 (2023).
• L.T. Giorgini, R. Eichorn, M. Das, W. Moon and J.S. Wettlaufer, The Thermodynamic Cost of Erasing Information in Finite-time, Phys. Rev. Res., 5, 023084 (2023).
• L.T. Giorgini, U.D. Jentschura, E.M. Malatesta, G. Parisi, T. Rizzo, and J. Zinn-Justin, Correlation Functions of the Anharmonic Oscillator: Numerical Verification of Two-Loop Corrections to the Large-Order Behavior, Phys. Rev. D, 105, 105012 (2022).
• L.T. Giorgini, W. Moon, N. Chen and J.S. Wettlaufer, A Non-Gaussian Stochastic Model for the El Niño Southern Oscillation, Phys. Rev. Res., 4, L022065 (2022).
• L.T. Giorgini, W. Moon, N. Chen and J.S. Wettlaufer, Modeling the El Niño Southern Oscillation with Neural Differential Equations, TSM-ICML (2021).
• W. Moon, L.T. Giorgini, and J.S. Wettlaufer, Nonadiabatic stochastic resonance: An analytical solution, Phys. Rev. E, 104, 044130 (2021).
• S.H. Lim, L.T. Giorgini, W. Moon, and J.S. Wettlaufer, Predicting rare events in multiscale dynamical systems using machine learning, Chaos, 30, 123126 (2020).
• L.T. Giorgini, U.D. Jentschura, E.M. Malatesta, G. Parisi, T. Rizzo, and J. Zinn-Justin, Two-loop corrections to the large-order behavior of correlation functions in the one-dimensional N-vector model, Phys. Rev. D, 101, 125001 (2020).
• L.T. Giorgini, W. Moon, and J.S. Wettlaufer, Analytical Survival Analysis of the Ornstein–Uhlenbeck Process, J. Stat. Phys., 181, 2404 (2020).
• L.T. Giorgini, S.H. Lim, W. Moon, and J.S. Wettlaufer, Precursors to rare events in stochastic resonance, EPL, 129, 40003 (2020) (Editor's choice).

Code

ClustGen.jl

This code implements a hybrid methodology for efficient score function estimation and response analysis in nonlinear stochastic systems. It combines a clustering-based Gaussian Mixture Model approach with neural network interpolation to estimate the score function from large datasets, and leverages the Generalized Fluctuation-Dissipation Theorem (GFDT) to construct higher-order response functions. The code is demonstrated on reduced-order models—including triad systems and slow-fast models relevant to climate dynamics—validating its ability to accurately capture non-Gaussian effects and predict system responses to small perturbations.

Contact

Email: ludogio@mit.edu

Office: Room 2-165

Address: Department of Mathematics, MIT, 77 Massachusetts Avenue, Cambridge, MA 02139

Please feel free to get in touch for collaborations, research inquiries, or any professional opportunities.