Base Models for Parabolic Partial Differential Equations
This work addresses a computational bottleneck for researchers and practitioners in fields like generative modeling, stochastic control, and finance, though it appears incremental as it builds upon existing meta-learning concepts.
The paper tackles the problem of efficiently solving parametric parabolic PDEs across different scenarios, which typically requires time-consuming recomputation from scratch, by proposing a meta-learning framework that learns a base distribution to improve generalization to new parameter regimes.
Parabolic partial differential equations (PDEs) appear in many disciplines to model the evolution of various mathematical objects, such as probability flows, value functions in control theory, and derivative prices in finance. It is often necessary to compute the solutions or a function of the solutions to a parametric PDE in multiple scenarios corresponding to different parameters of this PDE. This process often requires resolving the PDEs from scratch, which is time-consuming. To better employ existing simulations for the PDEs, we propose a framework for finding solutions to parabolic PDEs across different scenarios by meta-learning an underlying base distribution. We build upon this base distribution to propose a method for computing solutions to parametric PDEs under different parameter settings. Finally, we illustrate the application of the proposed methods through extensive experiments in generative modeling, stochastic control, and finance. The empirical results suggest that the proposed approach improves generalization to solving PDEs under new parameter regimes.