On the oracle complexity of first-order and derivative-free algorithms for smooth nonconvex minimization

ePubs

The open archive for STFC research publications

DOI	10.5286/raltr.2010029
Persistent URL	http://purl.org/net/epubs/work/53954
Record Status	Checked
Record Id	53954
Title	On the oracle complexity of first-order and derivative-free algorithms for smooth nonconvex minimization
Contributors	C Cartis (Edinburgh U.), NIM Gould (STFC Rutherford Appleton Lab.), PL Toint (Facultes Universitaires ND de la Paix)
Abstract	The (optimal) function/gradient evaluations worst-case complexity analysis available for the Adaptive Regularizations algorithms with Cubics (ARC) for nonconvex smooth unconstrained optimization is extended to finite-difference versions of this algorithm, yielding complexity bounds for first-order and derivative free methods applied on the same problem class. A comparison with the results obtained for derivative-free methods by Vicente (2010) is also discussed, giving some theoretical insight on the relative merits of various methods in this popular class of algorithms.
Organisation	CSE , CSE-NAG , STFC
Keywords
Funding Information
Related Research Object(s):	62623
Licence Information:
Language	English (EN)

Type	Details	URI(s)	Local file(s)	Year
Report	RAL Technical Reports RAL-TR-2010-029. 2010.		RAL-TR-2010-029.pdf	2010