PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A general projection property for distribution families
Y Yu, Y Li, Csaba Szepesvari and D Schuurmans
In: NIPS-22(2009).

Abstract

Surjectivity of linear projections between distribution families with fixed mean and covariance (regardless of dimension) is re-derived by a new proof. We further extend this property to distribution families that respect additional constraints, such as symmetry, unimodality and log-concavity. By combining our results with classic univariate inequalities, we provide new worst-case analyses for natural risk criteria arising in classification, optimization, portfolio selection and Markov decision processes.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:6365
Deposited By:Csaba Szepesvari
Deposited On:08 March 2010