Statistics Papers

Document Type

Conference Paper

Date of this Version


Publication Source

Conference on Information Sciences and Systems, Princeton University


The competitive complexity ratio is the worst case ratio of the regret of a data-driven model to that obtained by a model which benefits from side information. The side information bounds the sizes of unknown parameters. The ratio requires the use of a variation on parametric complexity, which we call the unconditional parametric complexity. We show that the optimal competitive complexity ratio is bounded and contrast this result with comparable results in statistics.



Date Posted: 27 November 2017