Kriging

This is the Wiki of a special interest group of people interested in Noisy Kriging-based Optimization, who had their first workshop in Bern, Switzerland, from Monday 22 to Wednesday 24 November 2010

To the workshop programme and info

Applications

• IRSN (criticality safety coefficient), 2 variables, 75*75 data points, 40 noise levels.
• Video game data (19 to 22 variables)
• Well placement, C Bürger, Matlab code + 1000 to 10000 given realizations of conductivity fields.
• M de Paly, idem with plant irigation problem, 1000 realizations, 15 to 100 variables (irrigation times and amounts)
• BBOB test case (C++ / Java with matlab interface)
• SPO test case ?
• Financial test case ?

Note : IRSN, video game, well placement are mono-obj problems, the irrigation is multi-obj or mono-obj

• A first collection of papers on noisy Kriging-based Optimization can be downloaded. Until an own subpage with a BibTeX plugin exists, please send changes and additional entries to Tobias Wagner.

Toolboxes and softwares for learning and optimization

• DICE: Olivier Roustant, David Ginsbourger
• SIMPLE Toolbox: Felipe A. C. Viana
• Scilab: Janis Janusevskis
• Matlab: Alexander Forrester
• SUMO: Dirk Gorissen
• Matlab/ GNU Octave Toolbox from Supelec: Emmanuel Vazquez, Julien Bect

A. Forrester : International Conf on Mathematical Programming might be a candidate for an NKO mini-symposium.