Xavier Warin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xavier Warin has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Peter Tankov
CREST, ENSAE, Institut polytechnique de Paris, 91120 Palaiseau, France
7 shared publications - Huyên Pham
Ecole Polytechnique, CMAP
6 shared publications - Clémence Alasseur
EDF Lab Saclay Palaiseau France
4 shared publications - Joseph Mikael
EDF R&D
4 shared publications - Marie Bernhart
Laboratoire de Probabilités et Modèles Aléatoires Universités Paris 6-Paris 7
4 shared publications - Maximilien Germain
Univ Paris Cite, EDF R&D, F-75013 Paris, France
4 shared publications
Latest Publications
- 7 September 2026
- Published by Springer Nature in Methodology and Computing in Applied Probability
- Vol. 28 (3) , 95
Deep Learning Algorithms for FBSDEs with Jumps: Applications to Option Pricing and a MFG Model for Smart Grids
- 7 September 2026
- Published by Springer Nature in Methodology and Computing in Applied Probability
- Vol. 28 (3) , 95
Deep Learning Algorithms for FBSDEs with Jumps: Applications to Option Pricing and a MFG Model for Smart Grids
- 2 September 2026
- Published by Wiley in Mathematical Finance
- Vol. 36 (4) , 626-662
Growth Model With Externalities for the Energy Transition
We introduce a novel mean‐field game model for multi‐sector economic growth in which a dynamically evolving externality, influenced by the collective action of countries, plays a central role. By integrating environmental considerations in classical growth models, the framework incorporates “common noise” to capture shared uncertainties about the externality variable. We establish the existence and uniqueness of a mean‐field game equilibrium by reformulating the equilibrium conditions as a Forward‐Backward Stochastic Differential Equation via the stochastic maximum principle, first applying a contraction‐mapping argument to guarantee a unique solution, then employing the concept of weak equilibria to prove existence under more general assumptions, and finally invoking a specific monotonicity regime to reaffirm uniqueness. We provide a numerical resolution for a specified model using a fixed‐point approach combined with neural network approximations.
- 2 September 2026
- Published by Wiley in Mathematical Finance
- Vol. 36 (4) , 626-662
Growth Model With Externalities for the Energy Transition
We introduce a novel mean‐field game model for multi‐sector economic growth in which a dynamically evolving externality, influenced by the collective action of countries, plays a central role. By integrating environmental considerations in classical growth models, the framework incorporates “common noise” to capture shared uncertainties about the externality variable. We establish the existence and uniqueness of a mean‐field game equilibrium by reformulating the equilibrium conditions as a Forward‐Backward Stochastic Differential Equation via the stochastic maximum principle, first applying a contraction‐mapping argument to guarantee a unique solution, then employing the concept of weak equilibria to prove existence under more general assumptions, and finally invoking a specific monotonicity regime to reaffirm uniqueness. We provide a numerical resolution for a specified model using a fixed‐point approach combined with neural network approximations.
- 26 August 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38 (16) , 703
P1-KAN: an effective kolmogorov-arnold network with application to hydraulic valley optimization
- 26 August 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38 (16) , 703
P1-KAN: an effective kolmogorov-arnold network with application to hydraulic valley optimization
- 17 June 2026
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 48 (3) , C579-C603
Input Convex Kolmogorov–Arnold Networks
This article presents an input convex neural network (ICNN) architecture using Kolmogorov–Arnold networks (ICKANs). Two specific networks are presented. The first is based on a low-order, piecewise-linear representation of functions, and a universal approximation theorem is provided. The second is based on cubic splines, for which only numerical results support convergence. We demonstrate through simple tests that these networks perform competitively with classical ICNNs. We then use the networks to solve optimal transport problems that require a convex approximation of functions and demonstrate their effectiveness. Cubic-ICKANs produce results similar to those of ICNNs.
- 17 June 2026
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 48 (3) , C579-C603
Input Convex Kolmogorov–Arnold Networks
This article presents an input convex neural network (ICNN) architecture using Kolmogorov–Arnold networks (ICKANs). Two specific networks are presented. The first is based on a low-order, piecewise-linear representation of functions, and a universal approximation theorem is provided. The second is based on cubic splines, for which only numerical results support convergence. We demonstrate through simple tests that these networks perform competitively with classical ICNNs. We then use the networks to solve optimal transport problems that require a convex approximation of functions and demonstrate their effectiveness. Cubic-ICKANs produce results similar to those of ICNNs.
- 14 February 2025
- Published by Springer Nature in Methodology and Computing in Applied Probability
- Vol. 27 (1) , 1-20
Actor-Critic Learning Algorithms for Mean-Field Control with Moment Neural Networks
- 14 February 2025
- Published by Springer Nature in Methodology and Computing in Applied Probability
- Vol. 27 (1) , 1-20
Actor-Critic Learning Algorithms for Mean-Field Control with Moment Neural Networks
- Open Access
Battery valuation on electricity intraday markets with liquidity costs
In this paper, we propose a complete modelling framework to value several batteries in the electricity intraday market at the trading session scale. The model consists of a stochastic model for the 24 mid-prices (one price per delivery hour) combined with a deterministic model for the liquidity costs (representing the cost of going deeper in the order book). A stochastic optimisation framework based on dynamic programming is used to calculate the value of the batteries. We carry out a back test for the years 2021, 2022 and 2023 for the German market and for the French market. We show that it is essential to take liquidity into account, especially when the number of batteries is large: it allows much higher profits and avoids high losses using our liquidity model. The use of our stochastic model for the mid-price also significantly improves the results (compared to a deterministic framework where the mid-price forecast is the spot price).
Open AccessBattery valuation on electricity intraday markets with liquidity costs
In this paper, we propose a complete modelling framework to value several batteries in the electricity intraday market at the trading session scale. The model consists of a stochastic model for the 24 mid-prices (one price per delivery hour) combined with a deterministic model for the liquidity costs (representing the cost of going deeper in the order book). A stochastic optimisation framework based on dynamic programming is used to calculate the value of the batteries. We carry out a back test for the years 2021, 2022 and 2023 for the German market and for the French market. We show that it is essential to take liquidity into account, especially when the number of batteries is large: it allows much higher profits and avoids high losses using our liquidity model. The use of our stochastic model for the mid-price also significantly improves the results (compared to a deterministic framework where the mid-price forecast is the spot price).
- 15 October 2024
- Published by Springer Nature in Dynamic Games and Applications
- Vol. 15 (2) , 417-453
Representation Results and Error Estimates for Differential Games with Applications Using Neural Networks
- 15 October 2024
- Published by Springer Nature in Dynamic Games and Applications
- Vol. 15 (2) , 417-453
Representation Results and Error Estimates for Differential Games with Applications Using Neural Networks
- 26 September 2023
- Published by Springer Nature in Partial Differential Equations and Applications
- Vol. 4 (5) , 1-36
Neural networks for first order HJB equations and application to front propagation with obstacle terms
- 26 September 2023
- Published by Springer Nature in Partial Differential Equations and Applications
- Vol. 4 (5) , 1-36
Neural networks for first order HJB equations and application to front propagation with obstacle terms
- Open Access
Mean-field neural networks: learning mappings on Wasserstein space
We study the machine learning task for models with operators mapping between the Wasserstein space of probability measures and a space of functions, like e.g. in mean-field games/control problems. Two classes of neural networks, based on bin density and on cylindrical approximation, are proposed to learn these so-called mean-field functions, and are theoretically supported by universal approximation theorems. We perform several numerical experiments for training these two mean-field neural networks, and show their accuracy and efficiency in the generalization error with various test distributions. Finally, we present different algorithms relying on mean-field neural networks for solving time-dependent mean-field problems, and illustrate our results with numerical tests for the example of a semi-linear partial differential equation in the Wasserstein space of probability measures.
Open AccessMean-field neural networks: learning mappings on Wasserstein space
We study the machine learning task for models with operators mapping between the Wasserstein space of probability measures and a space of functions, like e.g. in mean-field games/control problems. Two classes of neural networks, based on bin density and on cylindrical approximation, are proposed to learn these so-called mean-field functions, and are theoretically supported by universal approximation theorems. We perform several numerical experiments for training these two mean-field neural networks, and show their accuracy and efficiency in the generalization error with various test distributions. Finally, we present different algorithms relying on mean-field neural networks for solving time-dependent mean-field problems, and illustrate our results with numerical tests for the example of a semi-linear partial differential equation in the Wasserstein space of probability measures.
- 16 September 2023
- Published by Elsevier in Neural Networks
- Vol. 168, 380-393
Mean-field neural networks: Learning mappings on Wasserstein space
- 16 September 2023
- Published by Elsevier in Neural Networks
- Vol. 168, 380-393
Mean-field neural networks: Learning mappings on Wasserstein space