Bringing PDEs to JAX with forward and reverse modes automatic differentiation

Research output: Contribution to journalArticleScientific

4 Downloads (Pure)

Abstract

Partial differential equations (PDEs) are used to describe a variety of physical phenomena. Often these equations do not have analytical solutions and numerical approximations are used instead. One of the common methods to solve PDEs is the finite element method. Computing derivative information of the solution with respect to the input parameters is important in many tasks in scientific computing. We extend JAX automatic differentiation library with an interface to Firedrake finite element library. High-level symbolic representation of PDEs allows bypassing differentiating through low-level possibly many iterations of the underlying nonlinear solvers. Differentiating through Firedrake solvers is done using tangent-linear and adjoint equations. This enables the efficient composition of finite element solvers with arbitrary differentiable programs. The code is available at github.com/IvanYashchuk/jax-firedrake.
Original languageEnglish
JournalarXiv.org
Publication statusAccepted/In press - 1 Aug 2023
MoE publication typeB1 Non-refereed journal articles

Keywords

  • Computer Science - Mathematical Software
  • Computer Science - Machine Learning
  • Mathematics - Numerical Analysis

Fingerprint

Dive into the research topics of 'Bringing PDEs to JAX with forward and reverse modes automatic differentiation'. Together they form a unique fingerprint.

Cite this