OFFO minimization algorithms for second-order optimality and their complexity
Optimization and Control
2023-02-16 v1
Abstract
An Adagrad-inspired class of algorithms for smooth unconstrained optimization is presented in which the objective function is never evaluated and yet the gradient norms decrease at least as fast as while second-order optimality measures converge to zero at least as fast as . This latter rate of convergence is shown to be essentially sharp and is identical to that known for more standard algorithms (like trust-region or adaptive-regularization methods) using both function and derivatives' evaluations. A related "divergent stepsize" method is also described, whose essentially sharp rate of convergence is slighly inferior. It is finally discussed how to obtain weaker second-order optimality guarantees at a (much) reduced computional cost.
Cite
@article{arxiv.2203.03351,
title = {OFFO minimization algorithms for second-order optimality and their complexity},
author = {S. Gratton and Ph. L. Toint},
journal= {arXiv preprint arXiv:2203.03351},
year = {2023}
}