An optimal transport based geometry embedding, computed independently for each shape, improves accuracy and reduces compute for neural operator predictions of surface pressure and drag on car and airfoil benchmarks.
Polar factorization and monotone rearrangement of vector-valued functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Geometric Operator Learning with Optimal Transport
An optimal transport based geometry embedding, computed independently for each shape, improves accuracy and reduces compute for neural operator predictions of surface pressure and drag on car and airfoil benchmarks.