Random subspace derivative-free optimization is shown to reach second-order critical points in O~(n^4.5 epsilon^-3) evaluations, and a new subspace quadratic-model solver handles n ~ 1000 problems.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Randomized Subspace Derivative-Free Optimization with Quadratic Models and Second-Order Convergence
Random subspace derivative-free optimization is shown to reach second-order critical points in O~(n^4.5 epsilon^-3) evaluations, and a new subspace quadratic-model solver handles n ~ 1000 problems.