We propose an optimization method obtained by the approximation of a novel discretization approach for gradient dynamics recently proposed by the authors. It is shown that the proposed algorithm ensures convergence for all amplitudes of the step size, contrarily to classical implementations.
A gradient descent algorithm built on approximate discrete gradients / Moreschini, A.; Mattioni, M.; Monaco, S.; Normand-Cyrot, D.. - (2022), pp. 343-348. ((Intervento presentato al convegno 26th International Conference on System Theory, Control and Computing, ICSTCC 2022 tenutosi a Sinaia, Romania [10.1109/ICSTCC55426.2022.9931872].
A gradient descent algorithm built on approximate discrete gradients
Moreschini A.;Mattioni M.;Monaco S.;
2022
Abstract
We propose an optimization method obtained by the approximation of a novel discretization approach for gradient dynamics recently proposed by the authors. It is shown that the proposed algorithm ensures convergence for all amplitudes of the step size, contrarily to classical implementations.File allegati a questo prodotto
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
