Megadose AI progress, ranked and analyzed.

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

· ArXiv · AI/CL/LG ·
Pretraining helped most when target data was scarce, but the size of the gain changed with both airfoil coverage and modeled physics.

The paper pretrains a neural PDE surrogate on 254,909 RANS solutions from one airfoil family, then fine-tunes on another. With 1,000 target samples, pretraining matched scratch training with 3.25x more data for the same Spalart-Allmaras setup, versus 2.58x for the transition-modeled target. At 5,000 samples, that ordering flipped, with the transition-modeled target showing the larger relative gain. The authors also report that sampling more distinct target airfoils helped both targets at 1,000 samples, but the gain was clearly above draw-to-draw variation only in the same-SA case. ArXiv · AI/CL/LG's note

score 4

Categories: Research