A learned optimizer can predict fractional-order and step-size parameters, giving 99.2% convergence on Rosenbrock 2D when trained on that same function, but the underlying fractional-derivative approximation is unsupported.
R´esum´e des lec ¸ons donn´ees `a l’ ´ecole royale polytechnique sur le calcul infinit ´esimal, volume 1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Applications of fractional calculus in learned optimization
A learned optimizer can predict fractional-order and step-size parameters, giving 99.2% convergence on Rosenbrock 2D when trained on that same function, but the underlying fractional-derivative approximation is unsupported.