PCE coefficients, solved by least squares or PDE residuals, can serve as an operator learning surrogate that also yields UQ moments.
Learning nonlinear operators via deeponet based on the universal approximation theorem of operators,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Polynomial Chaos Expansion for Operator Learning
PCE coefficients, solved by least squares or PDE residuals, can serve as an operator learning surrogate that also yields UQ moments.