×

Replica approach to mean-variance portfolio optimization. (English) Zbl 1456.91118

Summary: We consider the problem of mean-variance portfolio optimization for a generic covariance matrix subject to the budget constraint and the constraint for the expected return, with the application of the replica method borrowed from the statistical physics of disordered systems. We find that the replica symmetry of the solution does not need to be assumed, but emerges as the unique solution of the optimization problem. We also check the stability of this solution and find that the eigenvalues of the Hessian are positive for \(r = N/T < 1\), where \(N\) is the dimension of the portfolio and \(T\) the length of the time series used to estimate the covariance matrix. At the critical point \(r = 1\) a phase transition is taking place. The out of sample estimation error blows up at this point as \(1/(1 - r)\), independently of the covariance matrix or the expected return, displaying the universality not only of the critical exponent, but also the critical point. As a conspicuous illustration of the dangers of in-sample estimates, the optimal in-sample variance is found to vanish at the critical point inversely proportional to the divergent estimation error.

MSC:

91G10 Portfolio theory

References:

[1] Markowitz H 1952 Portfolio selection J. Finance7 77-91 · doi:10.1111/j.1540-6261.1952.tb01525.x
[2] Markowitz H 1959 Portfolio Selection: Efficient Diversification of Investments (New York: Wiley)
[3] Merton R C 1972 An analytic derivation of the efficient portfolio frontier J. Financ. Quant. Anal.7 1851-72 · doi:10.2307/2329621
[4] Dickinson J P 1974 The reliability of estimation procedures in portfolio analysis J. Financ. Quant. Anal.9 447-62 · doi:10.2307/2329872
[5] Jobson J D and Korkie B 1979 Improved estimation for Markowitz portfolios using James-Stein type estimators Proc. of the American Statistical Association(Business and Economic Statistics,)vol 1 pp 279-84
[6] Frost P A and Savarino J E 1986 An empirical Bayes approach to efficient portfolio selection J. Financ. Quant. Anal.21 293-305 · doi:10.2307/2331043
[7] Jorion P 1986 Bayes-Stein estimation for portfolio analysis J. Financ. Quant. Anal.21 279-92 · doi:10.2307/2331042
[8] Konno H 1988 Portfolio optimization using l1 risk function Technical Report IHSS 88-9
[9] Konno H and Yamazaki H 1991 Mean-absolute deviation portfolio optimization model and its application to tokyo stock market Manage. Sci.37 519-31 · doi:10.1287/mnsc.37.5.519
[10] Elton E J and Gruber M J 1995 Modern Portfolio Theory and Investment Analysis (New York: Wiley)
[11] Young M R 1998 A minimax portfolio selection rule with linear programming solution Manage. Sci.44 673-83 · Zbl 0999.91043 · doi:10.1287/mnsc.44.5.673
[12] Artzner P, Delbaen F, Eber J-M and Heath D 1999 Coherent measures of risk Math. Finance9 203-28 · Zbl 0980.91042 · doi:10.1111/1467-9965.00068
[13] Gábor A and Kondor I 1999 Portfolios with nonlinear constraints and spin glasses Physica A 274 222-8 · doi:10.1016/S0378-4371(99)00387-8
[14] Laloux L, Cizeau P, Bouchaud J-P and Potters M 1999 Noise dressing of financial correlation matrices Phys. Rev. Lett.83 1467-70 · doi:10.1103/PhysRevLett.83.1467
[15] Plerou V, Gopikrishnan P, Rosenow B, Amaral L A N and Stanley H E 1999 Universal and non-universal properties of cross-correlations in financial time series Phys. Rev. Lett.83 1471-4 · doi:10.1103/PhysRevLett.83.1471
[16] Plerou V, Gopikrishnan P, Rosenow B, Amaral L A N, Guhr T and Stanley H E 2000 A random matrix approach to cross-correlations in financial time-series Phys. Rev. E 65 066126 · doi:10.1103/PhysRevE.65.066126
[17] Jorion P 2000 VaR: The New Benchmark for Managing Financial Risk (New York: McGraw-Hill)
[18] Laloux L, Cizeau P, Bouchaud J-P and Potters M 2000 Random matrix theory and financial correlations Int. J. Theor. Appl. Finance3 391 · Zbl 0970.91059 · doi:10.1142/S0219024900000255
[19] Rockafellar R T and Uryasev S 2000 Optimization of conditional value-at-risk J. Risk2 21-41 · doi:10.21314/JOR.2000.038
[20] Acerbi C and Tasche D 2002 Expected shortfall: a natural coherent alternative to value at risk Econ. Notes31 379-88 · doi:10.1111/1468-0300.00091
[21] Acerbi C and Tasche D 2002 On the coherence of expected shortfall J. Bank. Finance26 1487-503 · doi:10.1016/S0378-4266(02)00283-2
[22] Pafka S and Kondor I 2002 Noisy covariance matrices and portfolio optimization Eur. Phys. J. B 27 277-80 · doi:10.1140/epjb/e20020153
[23] Jagannathan R and Ma T 2003 Risk reduction in large portfolios: Why imposing the wrong constraints helps J. Finance58 1651-84 · doi:10.1111/1540-6261.00580
[24] Ledoit O and Wolf M 2003 Improved estimation of the covariance matrix of stock returns with an application to portfolio selection J. Empir. Finance10 603-21 · doi:10.1016/S0927-5398(03)00007-0
[25] Pafka S and Kondor I 2003 Noisy covariance matrices and portfolio optimization II Physica A 319 487-94 · Zbl 1008.91039 · doi:10.1016/S0378-4371(02)01499-1
[26] Ledoit O and Wolf M 2004 A well-conditioned estimator for large-dimensional covariance matrices J. Multivariate Anal.88 365-411 · Zbl 1032.62050 · doi:10.1016/S0047-259X(03)00096-4
[27] Pafka S and Kondor I 2004 Estimated correlation matrices and portfolio optimization Physica A 343 623-34 · doi:10.1016/j.physa.2004.05.079
[28] Scherer B and Martin R D 2005 Introduction to Modern Portflio Optimization With NUOPT and S-PLUS (Berlin: Springer) · Zbl 1104.90002 · doi:10.1007/978-0-387-27586-4
[29] Kempf A and Memmel C 2006 Estimating the global minimum variance portfolio Schmalenbach Bus. Rev.58 332-48 · doi:10.1007/BF03396737
[30] Okhrin Y and Schmid W 2006 Distributional properties of portfolio weights J. Econometrics134 235-56 · Zbl 1420.91430 · doi:10.1016/j.jeconom.2005.06.022
[31] Elton E J, Gruber M J, Brown S J and Goetzmann W N 2007 Modern Portfolio Theory and Investment Analysis (Hoboken, NJ: Wiley)
[32] Garlappi L, Uppal R and Wang T 2007 Portfolio selection with parameter and model uncertainty: a multi-prior approach Rev. Financ. Stud.20 41-81 · doi:10.1093/rfs/hhl003
[33] Golosnoy V and Okhrin Y 2007 Multivariate shrinkage for optimal portfolio weights Eur. J. Finance13 441-58 · doi:10.1080/13518470601137592
[34] Kan R and Zhou G 2007 Optimal portfolio choice with parameter uncertainty J. Financ. Quant. Anal.42 621-56 · doi:10.1017/S0022109000004129
[35] Fabozzi F J, Kolm P, Pachamanova D A and Focardi S M 2007 Robust Portfolio Optimization and Management (Hoboken, NJ: Wiley)
[36] Kondor I, Pafka S and Nagy G 2007 Noise sensitivity of portfolio selection under various risk measures J. Bank. Finance31 1545-73 · doi:10.1016/j.jbankfin.2006.12.003
[37] Varga-Haszonits I and Kondor I 2007 Noise sensitivity of portfolio selection in constant conditional correlation GARCH models Physica A 385 307-18 · doi:10.1016/j.physa.2007.06.017
[38] Frahm G 2010 Linear statistical inference for global and local minimum variance portfolios Stat. Pap.51 789-812 · Zbl 1247.91171 · doi:10.1007/s00362-008-0170-z
[39] Basak G K, Jagannathan R and Ma T 2009 A jackknife estimator for tracking error variance of optimal portfolios constructed using estimated inputs Manage. Sci.55 990-1002 · Zbl 1232.91644 · doi:10.1287/mnsc.1090.1001
[40] Brodie J, Daubechies I, De Mol C, Giannone D and Loris I 2009 Sparse and stable Markowitz portfolios Proc. Natl Acad. Sci.106 12267-72 · Zbl 1203.91271 · doi:10.1073/pnas.0904287106
[41] DeMiguel V, Garlappi L, Nogales F J and Uppal R 2009 A generalized approach to portfolio optimization: improving performance by constraining portfolio norms Manage. Sci.55 798-812 · Zbl 1232.91617 · doi:10.1287/mnsc.1080.0986
[42] DeMiguel V, Garlappi L and Uppal R 2009 Optimal versus naive diversification: How efficient is the 1/n portfolio strategy? Rev. Financ. Stud.22 1915-53 · doi:10.1093/rfs/hhm075
[43] Frahm G and Memmel C 2010 Dominating estimators for minimum-variance portfolios J. Econometrics159 289-302 · Zbl 1441.62264 · doi:10.1016/j.jeconom.2010.07.007
[44] Kondor I and Varga-Haszonits I 2010 Instability of portfolio optimization under coherent risk measures Adv. Complex Syst.13 425-37 · Zbl 1193.91139 · doi:10.1142/S0219525910002591
[45] Still S and Kondor I 2010 Regularizing portfolio optimization New J. Phys.12 075034 · Zbl 1445.91059 · doi:10.1088/1367-2630/12/7/075034
[46] Bun J, Bouchaud J-P and Potters M 2016 My beautiful laundrette: cleaning correlation matrices for portfolio optimization (https://researchgate.net/publication/302339055)
[47] Ciliberti S, Kondor I and Mézard M 2007 On the feasibility of portfolio optimization under expected shortfall Quant. Finance7 389-96 · Zbl 1190.91116 · doi:10.1080/14697680701422089
[48] Ciliberti S and Mézard M 2007 Risk minimization through portfolio replication Eur. Phys. J. B 57 175-80 · Zbl 1189.91191 · doi:10.1140/epjb/e2007-00130-7
[49] Caccioli F, Still S, Marsili M and Kondor I 2013 Optimal liquidation strategies regularize portfolio selection Eur. J. Finance19 554-71 · doi:10.1080/1351847X.2011.601661
[50] Caccioli F, Kondor I, Marsili M and Still S 2016 Liquidity risk and instabilities in portfolio optimization Int. J. Theor. Appl. Finance19 1650035 · Zbl 1396.91678 · doi:10.1142/S0219024916500357
[51] Kondor I, Caccioli F, Papp G and Marsili M 2015 Contour map of estimation error for expected shortfall (http://ssrn.com/abstract=2567876) (arXiv:1502.0621)
[52] Caccioli F, Kondor I and Papp G 2015 Portfolio optimization under expected shortfall: contour maps of estimation error (arXiv:1510.04943)
[53] Papp F, Caccioli G and Kondor I 2016 Variance-bias trade-off in portfolio optimization under expected shortfall with ℓ2 regularization (arXiv:1602.08297v1 [q-fin.PM])
[54] Basel Committee on Banking Supervision 2016 Minimum capital requirements for market risk Bank for International Settlements
[55] Shinzato T 2016 Minimal investment risk of portfolio optimization problem with budget and investment concentration constraints (arXiv:1605.06845v1 [q-fin.PM])
[56] Komjati B 2008 The instability of portfolio selection (unpublished MSc Thesis) Technical Report Eötvös University, Budapest
[57] Donoho D and Tanner J 2009 Observed universality of phase transitions in high-dimensional geometry, with implications for modern data analysis and signal processing Phil. Trans. R. Soc. A 367 4273-93 · Zbl 1185.94029 · doi:10.1098/rsta.2009.0152
[58] Kondor I and Varga-Haszonits I 2008 Divergent estimation error in portfolio optimization and in linear regression Eur. Phys. J. B 64 601-5 · Zbl 1189.91194 · doi:10.1140/epjb/e2008-00060-x
[59] Kirkpatrick S, Gelatt C D and Vecchi M P 1983 Optimization by simulated annealing Science220 671-80 · Zbl 1225.90162 · doi:10.1126/science.220.4598.671
[60] Guerra F and Toninelli F L 2002 The thermodynamic limit in mean field spin glass model Commun. Math. Phys.230 71-9 · Zbl 1004.82004 · doi:10.1007/s00220-002-0699-y
[61] Guerra F and Toninelli F L 2003 The infinite volume limit in generalized mean field disordered models Markov Process. Relat. Fields9 195-207 · Zbl 1033.82009
[62] Talagrand M 2003 Spin Glasses: a Challenge for Mathematicians: Cavity and Mean Field Models vol 46 (Berlin: Springer) · Zbl 1033.82002
[63] Burda Z, Jurkiewicz J and Nowak M A 2003 Is econophysics a solid science? Acta Phys. Pol. B 34 87-131
[64] Mézard M, Parisi G and Virasoro M A 1987 Spin Glass Theory and Beyond(World Scientific Lecture Notes in Physics vol 9) (Singapore: World Scientific) · Zbl 0992.82500
[65] Bühlmann P and Van De Geer S 2011 Statistics for High-Dimensional Data: Methods, Theory and Applications (Berlin: Springer) · Zbl 1273.62015 · doi:10.1007/978-3-642-20192-9
[66] Mezard M and Montanari A 2009 Information, Physics, and Computation (Oxford: Oxford University Press) · Zbl 1163.94001 · doi:10.1093/acprof:oso/9780198570837.001.0001
[67] Amelunxen D, Lotz M, McCoy M B and Tropp J A 2013 Living on the edge: a geometric theory of phase transitions in convex optimization Technical Report DTIC Document
[68] Schmidt B K and Mattheiss T H 1977 The probability that a random polytope is bounded Math. Oper. Res.2 292-6 · Zbl 0392.52010 · doi:10.1287/moor.2.3.292
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.