Strong Convergence to the Mean-Field Limit of A Finite Agent Equilibrium
We study an equilibrium-based continuous asset pricing problem for the securities market. In the previous work [16], we have shown that a certain price process, which is given by the solution to a forward backward stochastic differential equation of conditional McKean-Vlasov type, asymptotically clears the market in the large population limit. In the current work, under suitable conditions, we show the existence of a finite agent equilibrium and its strong convergence to the corresponding mean-field limit given in [16]. As an important byproduct, we get the direct estimate on the difference of the equilibrium price between the two markets; one consisting of heterogeneous agents of finite population size and the other of homogeneous agents of infinite population size.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
On the Convergence of Min-Max Langevin Dynamics and Algorithm
We study zero-sum games in the space of probability distributions over the Euclidean space $\mathbb{R}^d$ with entropy regularization, in the setting when the interaction function between the players is smooth and strong…
A Mean-Field Analysis of Multi-Head Self-Attention under Cross-Entropy Training
This paper develops a mean-field theory for a simplified single-layer causal multi-head self-attention model trained by cross-entropy minimization. Each attention head is treated as a particle in parameter space, and the…
Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces
We establish the convergence of the deep actor-critic reinforcement learning algorithm presented in [Angiuli et al., 2023a] in the setting of continuous state and action spaces with an infinite discrete-time horizon. Thi…
Reinforcement LearningGlobal convergence of ResNets: From finite to infinite width using linear parameterization
Overparametrization is a key factor in the absence of convexity to explain global convergence of gradient descent (GD) for neural networks. Beside the well studied lazy regime, infinite width (mean field) analysis has be…
Convergence of two-timescale gradient descent ascent dynamics: finite-dimensional and mean-field perspectives
The two-timescale gradient descent-ascent (GDA) is a canonical gradient algorithm designed to find Nash equilibria in min-max games. We analyze the two-timescale GDA by investigating the effects of learning rate ratios o…