AI RESEARCH
Diagnosing Failure Modes of Neural Operators Across Diverse PDE Families
arXiv CS.LG
•
ArXi:2601.11428v4 Announce Type: replace Neural PDE solvers have shown strong performance on standard benchmarks, but their robustness under deployment-relevant distribution shifts remains insufficiently characterized. We present a systematic stress-testing framework for evaluating neural PDE solvers across five qualitatively different PDE families -- dispersive, elliptic, multi-scale fluid, financial, and chaotic systems -- under controlled shifts in parameters, boundary or terminal conditions, resolution, rollout horizon, and input perturbations.