Optimal Newton-type methods for nonconvex smooth optimization

Add to your list(s) Download to your calendar using vCal

• Coralia Cartis (School of Mathematics, University of Edinburgh, UK)
• Thursday 13 September 2012, 15:00-16:00
• MR 14, Centre for Mathematical Sciences.

If you have a question about this talk, please contact Carola-Bibiane Schoenlieb.

This talk addresses global rates of convergence and the worst-case evaluation complexity of methods for nonconvex optimization problems. We show that the classical steepest-descent and Newton’s methods for unconstrained nonconvex optimization under standard assumptions may both require a number of iterations and function evaluations arbitrarily close to the steepest-descent’s global worst-case complexity bound. This implies that the latter upper bound is essentially tight for steepest descent and that Newton’s method may be as slow as the steepest-descent method in the worst case. Then the cubic regularization of Newton’s method (Griewank (1981), Nesterov & Polyak (2006)) is considered and extended to large-scale problems, while preserving the same order of its improved worst-case complexity (by comparison to that of steepest-descent); this improved worst-case bound is also shown to be tight. We further show that the cubic regularization approach is, in fact, optimal from a worst-case complexity point of view amongst a wide class of second-order methods for nonconvex optimization. The worst-case problem-evaluation complexity of constrained optimization will also be discussed. This is joint work with Nick Gould (Rutherford Appleton Laboratory, UK) and Philippe Toint (University of Namur, Belgium).

This talk is part of the Applied and Computational Analysis series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• Applied and Computational Analysis
• CMS Events
• DAMTP info aggregator
• Featured lists
• MR 14, Centre for Mathematical Sciences

Note that ex-directory lists are not shown.