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.
2022, 2022 26th International Conference on System Theory, Control and Computing, ICSTCC 2022 - Proceedings, Pages 343-348
A gradient descent algorithm built on approximate discrete gradients (04b Atto di convegno in volume)
Moreschini A., Mattioni M., Monaco S., Normand-Cyrot D.
Gruppo di ricerca: Nonlinear Systems and Control