How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates?

Paper recorded by Signals 4 on 2026-09-17 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18

Category: cs.LG · 机器学习 · first seen 2026-09-18

Abstract

Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes. However, it remains unclear how different components of distribution shift affect this benefit. We pretrain a surrogate on 254,909 RANS solutions from one airfoil family and fine-tune it on a new family under two target settings with matched freestream ranges: the same Spalart-

Read on arXiv →