English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We establish or refute the optimality of inexact second-order methods for unconstrained nonconvex optimization from the point of view of worst-case evaluation complexity, improving and generalizing the results of Cartis, Gould and Toint (2010,2011). To this aim, we consider a new general class of inexact second-order algorithms for unconstrained optimization that includes regularization and trust-region variations of Newton's method as well as of their linesearch variants. For each method in this class and arbitrary accuracy threshold $\epsilon \in (0,1)$, we exhibit a smooth objective function with bounded range, whose gradient is globally Lipschitz continuous and whose Hessian is $\alpha-$H\"older continuous (for given $\alpha\in [0,1]$), for which the method in question takes at least $\lfloor\epsilon^{-(2+\alpha)/(1+\alpha)}\rfloor$ function evaluations to generate a first iterate whose gradient is smaller than $\epsilon$ in norm. Moreover, we also construct another function on which Newton's takes $\lfloor\epsilon^{-2}\rfloor$ evaluations, but whose Hessian is Lipschitz continuous on the path of iterates. These examples provide lower bounds on the worst-case evaluation complexity of methods in our class when applied to smooth problems satisfying the relevant assumptions. Furthermore, for $\alpha=1$, this lower bound is of the same order in $\epsilon$ as the upper bound on the worst-case evaluation complexity of the cubic and other methods in a class of methods proposed in Curtis, Robinson and samadi (2017) or in Royer and Wright (2017), thus implying that these methods have optimal worst-case evaluation complexity within a wider class of second-order methods, and that Newton's method is suboptimal.

WORST-CASE EVALUATION COMPLEXITY AND OPTIMALITY OF SECOND-ORDER METHODS FOR NONCONVEX SMOOTH OPTIMIZATION