nips nips2009 nips2009-11 nips2009-11-reference knowledge-graph by maker-knowledge-mining

11 nips-2009-A General Projection Property for Distribution Families


Source: pdf

Author: Yao-liang Yu, Yuxi Li, Dale Schuurmans, Csaba Szepesvári

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. 1


reference text

[1] R. Jagannathan. “Minimax procedure for a class of linear programs under uncertainty”. Operations Research, vol. 25(1):pp. 173–177, 1977.

[2] Gert R.G. Lanckriet, Laurent El Ghaoui, Chiranjib Bhattacharyya and Michael I. Jordan. “A robust minimax approach to classification”. Journal of Machine Learning Research, vol. 03:pp. 555–582, 2002.

[3] G.C.Calafiore and Laurent El Ghaoui. “On distributionally robust chance-constrained linear programs”. Journal of Optimization Theory and Applications, vol. 130(1):pp. 1–22, 2006.

[4] Laurent El Ghaoui, Maksim Oks and Francois Oustry. “Worst-case value-at-risk and robust portfolio optimization: a conic programming approach”. Operations Research, vol. 51(4):pp. 542–556, 2003.

[5] Shu-Shang Zhu and Masao Fukushima. “Worst-case conditional value-at-risk with application to robust portfolio management”. Operations Research, vol. 57(5):pp. 1155–1168, 2009.

[6] Ioana Popescu. “Robust mean-covariance solutions for stochastic optimization”. Operations Research, vol. 55(1):pp. 98–112, 2007.

[7] Andr´ s Pr´ kopa. Stochastic Programming. Springer, 1995. a e

[8] Erick Delage and Shie Mannor. “Percentile optimization for Markov decision processes with parameter uncertainty”. Operations Research, to appear 2009.

[9] Li Chen, Simai He and Shuzhong Zhang. “Tight Bounds for Some Risk Measures, with Applications to Robust Portfolio Selection”. Tech. rep., Department of Systerms Engineering and Engineering Management, The Chinese University of Hongkong, 2009.

[10] Sudhakar Dharmadhikari and Kumar Joag-Dev. Unimodality, Convexity, and Applications. Academic Press, 1988.

[11] Dimitris Bertsimas and Ioana Popescu. “Optimal inequalities in probability theory a convex optimization approach”. SIAM Journal on Optimization, vol. 15(3):pp. 780–804, 2005.

[12] Albert W. Marshall and Ingram Olkin. “Multivariate Chebyshev inequalities”. Annals of Mathematical Statistics, vol. 31(4):pp. 1001–1014, 1960.

[13] Ioana Popescu. “A semidefinite programming approach to optimal moment bounds for convex classes of distributions”. Mathematics of Operations Research, vol. 30(3):pp. 632–657, 2005.

[14] R. Tyrrell Rockafellar and Stanislav Uryasev. “Optimization of conditional value-at-risk”. Journal of Risk, vol. 2(3):pp. 493–517, 2000.

[15] Ky Fan. “Minimax Theorems”. vol. 39(1):pp. 42–47, 1953. Proceedings of the National Academy of Sciences,

[16] Akiko Takeda and Masashi Sugiyama. “ν-support vector machine as conditional value-at-risk minimization”. In Proceedings of the 25th International Conference on Machine Learning, pp. 1056–1063. 2008.

[17] John Shawe-Taylor and Nello Cristianini. “Estimating the moments of a random vector with applications”. In Proceedings of GRETSI 2003 Conference, pp. 47–52. 2003. 9