Breakeven complexity is introduced to evaluate neural PDE solvers by total end-to-end cost, with results indicating they become advantageous for harder problems such as higher dimensions, longer rollouts, and higher Reynolds numbers.
To decrease the simulation resolution, we increase the timestepping parameters dt and pseudo-dt
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Breakeven complexity: A new perspective on neural partial differential equation solvers
Breakeven complexity is introduced to evaluate neural PDE solvers by total end-to-end cost, with results indicating they become advantageous for harder problems such as higher dimensions, longer rollouts, and higher Reynolds numbers.