Deep Learning and Elicitability for McKean-Vlasov FBSDEs With Common Noise
This addresses computational challenges in mean-field games and systemic risk modeling for researchers in mathematical finance and economics, though it appears incremental as it builds on existing deep learning and elicitability techniques.
The paper tackles the problem of solving McKean-Vlasov forward-backward stochastic differential equations with common noise by developing a numerical method that combines Picard iterations, elicitability, and deep learning, demonstrating accurate recovery of true solutions in a systemic risk model and applicability to complex economic models without closed-form solutions.
We present a novel numerical method for solving McKean-Vlasov forward-backward stochastic differential equations (MV-FBSDEs) with common noise, combining Picard iterations, elicitability and deep learning. The key innovation involves elicitability to derive a path-wise loss function, enabling efficient training of neural networks to approximate both the backward process and the conditional expectations arising from common noise - without requiring computationally expensive nested Monte Carlo simulations. The mean-field interaction term is parameterized via a recurrent neural network trained to minimize an elicitable score, while the backward process is approximated through a feedforward network representing the decoupling field. We validate the algorithm on a systemic risk inter-bank borrowing and lending model, where analytical solutions exist, demonstrating accurate recovery of the true solution. We further extend the model to quantile-mediated interactions, showcasing the flexibility of the elicitability framework beyond conditional means or moments. Finally, we apply the method to a non-stationary Aiyagari--Bewley--Huggett economic growth model with endogenous interest rates, illustrating its applicability to complex mean-field games without closed-form solutions.