Weak baselines
Weak baselines and reporting biases in ML for fluid PDEs
Paper title Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
Paper arXiv 2407.07218PDF
A systematic review of papers that use machine learning to solve fluid-related PDEs and claim to beat a numerical method, scored on two rules: compare at equal accuracy or equal runtime, and compare with an efficient numerical method. Ten highly cited results are re-run against a stronger baseline.
- Published
- Nature Machine Intelligence
Share on LinkedIn, X or Bluesky, or or .
Know related work that belongs here? Suggest a link
Something wrong on this page? Tell the editor