Recent papers

• Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching (with R. Denkert and X. Warin)

Submitted, arXiv: 2404.17939

• Nonlinear graphon mean-field systems (with F. Coppini and A. De Crescenzo)

Submitted, [arXiv:2402.08628]

• Actor critic learning algorithms for mean field control with moment neural networks (with X. Warin)

Submitted, [arXiv:2309.04317]

• Opinion dynamics in communities with major influencers and implicit  social influence via mean-field approximation (with D. Coculescu and M. Motte)

     To appear in Mathematics and Financial Economics, DOI : 10.1007/s11579-024-00355-1, [arXiv:2306.16553]

• Generative modeling for time series via Schrödinger bridge (with M. Hamdouche and P. Henry-Labordère)

     Submitted, [ResearchGate], [arXiv:2304.05093]

• Actor-critic learning for mean-field control in continuous time (with N. Frikha, M. Germain, M. Laurière, and X. Song)

Submitted, [ResearchGate], [arXiv:2303.06993]

• Policy gradient learning methods for stochastic control with exit time and applications to share repurchase pricing (with M. Hamdouche and P. Henry-Labordère)

Applied Mathematical Finance, 2023, 29(6), 439-456,   [ResearchGate], [SSRN]

• Mean-field neural networks-based  algorithms for McKean-Vlasov control problems (with X. Warin)

     To appear in Journal of Machine Learning, [ResearchGate], [arXiv:2212.11518]

• Mean-field neural networks: learning mappings on Wasserstein space, (with X. Warin)

Neural Networks, 2023, vol. 168, 380-393, https://doi.org/10.1016/j.neunet.2023.09.015, [ResearchGate], [arXiv:2210.15179]

• Quantitative propagation of chaos for mean field Markov decision process with common noise (with M. Motte)

Electronic Journal of Probability, 2023, Vol 28, 1-24.  [ResearchGate], [arXiv:2207.12738],

• Differential learning methods for solving fully nonlinear PDEs (with W. Lefebvre, G. Loeper)

Digital Finance, 2023, vol 5, 183-229,   [Researchgate],[arXiv:2205:09815]

• A level-set approach to the control of state-constrained McKean-Vlasov equations: application to renewable energy storage and portfolio selection (with M. Germain, X. Warin)

Numerical Algebra, Control and Optimization, special volume in honor of Jin Ma, 2023, vol 13(3&4): 555-582, [arXiv:2112.11059]  

• Optima bidding strategies for digital advertising  (with M. Motte)

[Researchgate],   [arXiv:2111.08311]

• Master Bellman equation in the Wasserstein space: Uniqueness of viscosity solutions  (with A. Cosso, F. Gozzi, I. Kharroubi, M. Rosestolato)

Transactions of the American Mathematical Society, 2024, vol. 377, 31-83.  DOI: https://doi.org/10.1090/tran/8986, [arXiv:2107.10535], 

• Neural networks-based algorithms for stochastic control and PDEs in finance (with M. Germain, X. Warin)

Machine Learning and Data Sciences for Financial Markets: a guide to contemporary practices, Cambridge University Press, Editors: Agostino Capponi and Charles-Albert Lehalle, [arXiv:2101.08068]

• Optimal control of path-dependent McKean-Vlasov SDEs in infinite dimension (with A. Cosso, F. Gozzi, I. Kharroubi, M. Rosestolato)

Annals of Applied Probability, 2023, 33(4), 2863-2918, DOI: 10.1214/22-AAP1880, [Researchgate], [arXiv:2012.14772]

• Itô’s formula for flow of measures on semimartingales (with X. Guo, X. Wei)

Stochastic Processes and their Applications, 2023, Vol. 159, pp 350-390, https://doi.org/10.1016/j.spa.2023.02.004, [arXiv:2010.05288]