A surrogate trained with Sobolev learning accelerates a finite-difference derivative-free method, with a complexity bound that improves with the average number of successful surrogate steps.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing finite-difference based derivative-free optimization methods with machine learning
A surrogate trained with Sobolev learning accelerates a finite-difference derivative-free method, with a complexity bound that improves with the average number of successful surrogate steps.