General mean-field BSDEs with integrable terminal values

Abstract

This paper investigates $L^1$ solutions for mean-field backward stochastic differential equations (MFBSDEs) under different weak assumptions in both one-dimensional and multi-dimensional settings, whose generator $f(\ddot{I}‰,t,y,z,\hat{I}¼)$ depends not only on the solution process $(Y,Z)$ but also on the law of $(Y,Z)$. In the one-dimensional case where $f$ depends on the law of $Y$, we show with the help of a test function method and a localization procedure that such type of equations with an integrable terminal condition admits an $L^1$ solution, when the generator $f(\ddot{I}‰,t,y,z,\hat{I}¼)$ has a one-sided linear growth in $(y,\hat{I}¼)$, and an iterated-logarithmically sub-linear growth in $z$. Furthermore, by leveraging the additional extended monotonicity in $y$ and an iterated-logarithmically uniform continuity in $z$ of the generator $f(\ddot{I}‰,t,y,z,\hat{I}¼)$ together with a strengthened nondecreasing condition in $\hat{I}¼$, we derive a comparison theorem for $L^1$ solutions, which immediately leads to the uniqueness of the $L^1$ solutions. Next, we establish the existence and the uniqueness of $L^1$ solutions for multi-dimensional mean-field BSDEs with integrable parameters in which the generator $f(\ddot{I}‰,t,y,z,\hat{I}¼)$ depends on $\hat{I}¼={\mathbb{P}}_Y$ and satisfies a one-sided Osgood condition as well as a general growth condition in $y$, a Lipschitz continuity as well as a sublinear growth condition in $z$, and a Lipschitz condition in $\hat{I}¼$. Finally, the solvability of $L^1$ solutions for general MFBSDEs is studied, where the generator $f(\ddot{I}‰,t,y,z,\hat{I}¼)$ depends on both the solution process $(Y,Z)$ and its joint law ${\mathbb{P}}_{(Y,Z)}$.

37pages