论文信息 - Evaluation complexity bounds for smooth constrained nonlinear optimisation using scaled KKT conditions, high-order models and the criticality measure $χ$

Evaluation complexity bounds for smooth constrained nonlinear optimisation using scaled KKT conditions, high-order models and the criticality measure $χ$

Evaluation complexity for convexly constrained optimization is considered and it is shown first that the complexity bound of $O(\epsilon^{-3/2})$ proved by Cartis, Gould and Toint (IMAJNA 32(4) 2012, pp.1662-1695) for computing an $\epsilon$-approximate first-order critical point can be obtained under significantly weaker assumptions. Moreover, the result is generalized to the case where high-order derivatives are used, resulting in a bound of $O(\epsilon^{-(p+1)/p})$ evaluations whenever derivatives of order $p$ are available. It is also shown that the bound of $O(\epsilon_P^{-1/2}\epsilon_D^{-3/2})$ evaluations ($\epsilon_P$ and $\epsilon_D$ being primal and dual accuracy thresholds) suggested by Cartis, Gould and Toint (SINUM, 2015) for the general nonconvex case involving both equality and inequality constraints can be generalized to a bound of $O(\epsilon_P^{-1/p}\epsilon_D^{-(p+1)/p})$ evaluations under similarly weakened assumptions. This paper is variant of a companion report (NTR-11-2015, University of Namur, Belgium) which uses a different first-order criticality measure to obtain the same complexity bounds.

[1] S. Łojasiewicz. Ensembles semi-analytiques , 1965 .

[2] P. Toint,et al. An adaptive cubic regularization algorithm for nonconvex optimization with convex constraints and its function-evaluation complexity , 2012 .

[3] Nicholas I. M. Gould,et al. On the Evaluation Complexity of Cubic Regularization Methods for Potentially Rank-Deficient Nonlinear Least-Squares Problems and Its Relevance to Constrained Nonlinear Optimization , 2013, SIAM J. Optim..

[4] Nicholas I. M. Gould,et al. On the complexity of finding first-order critical points in constrained nonlinear optimization , 2014, Math. Program..

[5] Nicholas I. M. Gould,et al. On the Evaluation Complexity of Constrained Nonlinear Least-Squares and General Constrained Nonlinear Optimization Using Second-Order Methods , 2015, SIAM J. Numer. Anal..

[6] José Mario Martínez,et al. Evaluation Complexity for Nonlinear Constrained Optimization Using Unscaled KKT Conditions and High-Order Models , 2016, SIAM J. Optim..

[7] José Mario Martínez,et al. Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models , 2017, Math. Program..

[8] P. Toint,et al. Evaluation Complexity Bounds for Smooth Constrained Nonlinear Optimization Using Scaled KKT Conditions and High-Order Models , 2019, Approximation and Optimization.