Non-exchangeable mean field Markov decision process with common noise: from Bellman equation to propagation of chaos
(with S. Mekkaoui), Hal-0550160
LightSBB-M: Bridging Schrödinger and Bass for generative modeling
(with A. Alouadi, P. Henry-Labordère, G. Loeper, O. Mazhar, N. Touzi), arXiv:2601.19312
A PDE derivation of the Schrödinger-Bass Bridge
(with A. Alouadi, P. Henry-Labordère, G. Loeper, O. Mazhar, N. Touzi), arXiv:2601.17863
Model-free policy gradient for discrete-time mean-field control
(with M. Meunier and C. Reisinger), arXiv:2601.11217,
Optimal control of McKean-Vlasov systems under partial observation and hidden Markov switching
(with M. Fuhrman and S. Ruda), arXiv:2601.09311,
Stochastic maximum principle for optimal control of non exchangeable mean-field systems
(with I. Kharroubi and S. Mekkaoui), arXiv:2506.05595,
Robust time series generation via Schrödinger bridge: a comprehensive evaluation
(with A. Alouadi, B. Barreau and L. Carlier), to appear in Proceedings of ICAIF'25, arXiv: 2503.02943, https://doi.org/10.1145/3768292.3770391
Linear-quadratic optimal control for non-exchangeable mean field SDEs and applications to systemic risk
(with A. De Crescenzo and F. De Feo), submitted, arXiv:2503.03318
Trading with propagators and constraints: applications to optimal execution and optimal storage
(with E. Abi Jaber and N. De Carvalho), submitted, arXiv:2409.12098
Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean field control problem in continuous time with common noise
(with N. Frikha and X. Song), submitted, arXiv:2408.02489
Mean field control of non exchangeable systems (with A. De Crescenzo, M. Fuhrman, I. Kharroubi)
to appear in ESAIM COCV, https://doi.org/10.1051/cocv/2025090, arXiv:2407.18635
Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching (with R. Denkert and X. Warin)
Applied Mathematics and Optimization, 2025, vol. 91(9), DOI: https://doi.org/10.1007/s00245-024-10207-5 arXiv: 2404.17939
Nonlinear graphon mean-field systems (with F. Coppini and A. De Crescenzo)
Stochastic Processes and their Applications, 2025, vol. 190, https://doi.org/10.1016/j.spa.2025.104728
Actor critic learning algorithms for mean field control with moment neural networks (with X. Warin)
Methodology and Computing in Applied Probability, 2025, vol. 27(13). DOI:https://doi.org/10.1007/s11009-025-10142-0 [arXiv:2309.04317]
A randomisation method for mean-field control problems with common noise (with R. Denkert and I. Kharroubi)
to appear in Electronic Journal of Probability, [arXiv: 2412.20782], https://doi.org/10.1214/25-EJP1453
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)
Journal of Machine Learning Research (JMLR), 2025, vol. 26, 1-42.
Optima bidding strategies for digital advertising (with M. Motte)
[Researchgate], [arXiv:2111.08311]