Joseph Teran — accepted AI-conference papers

2024

A Neural-Preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions

Kai Weixian Lan, Elias Gueidon, Ayano Kaneda, Julian Panetta, Joseph Teran

ICML 2024poster

We introduce a neural-preconditioned iterative solver for Poisson equations with mixed boundary conditions. Typical Poisson discretizations yield large, ill-conditioned linear systems. Iterative solvers can be effective for these problems, but only when equipped with powerful preconditioners. Unfort…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

A Deep Conjugate Direction Method for Iteratively Solving Linear Systems

Ayano Kaneda, Osman Akar, Jingyu Chen, Victoria Alicia Trevino Kala, David Hyde, Joseph Teran

ICML 2023poster

We present a novel deep learning approach to approximate the solution of large, sparse, symmetric, positive-definite linear systems of equations. Motivated by the conjugate gradients algorithm that iteratively selects search directions for minimizing the matrix norm of the approximation error, we de…

Cited by 9 Source ↗PDF ↗Scholar ↗