Andrea Agazzi's home page

Andrea Agazzi (andrea.agazzi at
Assistant Professor (RTD/b)
Mathematics Department, Università di Pisa
Largo Bruno Pontecorvo 5,
56127 Pisa PI, Italy

Didattica UNIPI

  1. Statistica I (Ingegneria Gestionale, a.a. 2022/23)

Research Interests

I am interested in applied probability theory, more specifically in interacting particle systems for real world applications. I have worked on scaling limits for models of chemical reaction networks, focusing on the relations between their dynamics and their structure. More recently, I have worked on the dynamics of scaling limits of machine learning algorithms seen as interacting particle systems, and on dynamics of fluid models.

Publications and Preprints (see also vitae or Google Scholar Page)

  1. Random Splitting of Fluid Models: Positive Lyapunov Exponents, with O. Melikechi and J. Mattingly, arXiv:2210.02958
  2. Random Splitting of Fluid Models: Ergodicity and Convergence, with O. Melikechi and J. Mattingly, arXiv:2201.06643
  3. A homotopic approach to policy gradients for linear quadratic regulators with nonlinear controls, with C. Chen, arXiv:2112.07612
  4. Large deviations with Markov jump processes with uniformly diminishing rates, with L. Andreis, M. Renger, R. Patterson, to appear in Stochastic Processes and Their Applicatons (arXiv:2102.13040)
  5. Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime, with J. Lu, International Conference on Learning Representations, 2021
  6. Temporal Difference Learning with nonlinear function approximation in the lazy training regime, with J. Lu, Proceedings of Machine Learning Research, Mathematical and Scientific Machine Learning, 2021
  7. Seemingly stable chemical kinetics can be stable, marginally stable or unstable, with J. Mattingly, Comm. Math. Sci. 18 (6), 1605 - 1642 (2020)
  8. Large Deviations Theory for Markov Jump Models of Chemical Reaction Networks, with A. Dembo and J.-P. Eckmann, Ann. Appl. Prob. 28 (3), 1821-1855 (2018)
  9. On the Geometry of Chemical Network Theory: Lyapunov Function and Large Deviations Theory, with A. Dembo and J.-P. Eckmann, J. Stat. Phys. 172 (2), 321-352 (2018)
  10. The Colored Hofstadter Butterfly for the Honeycomb Lattice, with G. M. Graf and J.-P. Eckmann, J. Stat. Phys. 156 (3), 417-426 (2014)


  1. Statistical Learning Theory (STATS 303, Duke)
  2. Stochastic Calculus (MATH 545, Duke)
  3. Introducton to Probabilty and Statistics (STATS 210, Duke)
  4. Probability theory (MATH 230, Duke)