An algorithm for maximizing expected log investment return

Let the random (stock market) vector X \geq 0 be drawn according to a known distribution function F(x), x \in R^{m} . A log-optimal portfolio b^{\ast} is any portfolio b achieving maximal expected \log return W^{\ast}=\sup_{b} E \ln b^{t}X , where the supremum is over the simplex b \geq 0, \sum_{i=1}^{m} b_{i} = 1 . An algorithm is presented for finding b^{\ast} . The algorithm consists of replacing the portfolio b by the expected portfolio b^{'}, b_{i}^{'} = E(b_{i}X_{i}/b^{t}X) , corresponding to the expected proportion of holdings in each stock after one market period. The improvement in W(b) after each iteration is lower-bounded by the Kullback-Leibler information number D(b^{'}\|b) between the current and updated portfolios. Thus the algorithm monotonically improves the return W . An upper bound on W^{\ast} is given in terms of the current portfolio and the gradient, and the convergence of the algorithm is established.

[1]  J. B. Williams Speculation and the Carryover , 1936 .

[2]  John L. Kelly,et al.  A new interpretation of information rate , 1956, IRE Trans. Inf. Theory.

[3]  H. Latané Criteria for Choice Among Risky Ventures , 1959, Journal of Political Economy.

[4]  L. Breiman Optimal Gambling Systems for Favorable Games , 1962 .

[5]  P. Samuelson General Proof that Diversification Pays , 1967, Journal of Financial and Quantitative Analysis.

[6]  E. Thorp OPTIMAL GAMBLING SYSTEMS FOR FAVORABLE GAMES , 1969 .

[7]  N. H. Hakansson.,et al.  Optimal Growth Portfolios When Yields Are Serially Correlated , 1970 .

[8]  N. H. Hakansson. Capital Growth and the Mean-Variance Approach to Portfolio Selection , 1971, Journal of Financial and Quantitative Analysis.

[9]  Suguru Arimoto,et al.  An algorithm for computing the capacity of arbitrary discrete memoryless channels , 1972, IEEE Trans. Inf. Theory.

[10]  Richard E. Blahut,et al.  Computation of channel capacity and rate-distortion functions , 1972, IEEE Trans. Inf. Theory.

[11]  W. Ziemba Note on “Optimal Growth Portfolios When Yields are Serially Correlated” , 1972, Journal of Financial and Quantitative Analysis.

[12]  E. Thorp,et al.  The Capital Growth Model: An Empirical Investigation , 1973, Journal of Financial and Quantitative Analysis.

[13]  Imre Csiszár,et al.  On the computation of rate-distortion functions (Corresp.) , 1974, IEEE Trans. Inf. Theory.

[14]  E. Thorp Portfolio Choice and the Kelly Criterion , 1975 .

[15]  James A. Ohlson,et al.  Portfolio Selection in a Lognormal Market When the Investor Has a Power Utility Function , 1976, Journal of Financial and Quantitative Analysis.

[16]  J. Kallberg,et al.  On the robustness of the Arrow-Pratt risk aversion measure , 1979 .

[17]  Robert M. Bell,et al.  Competitive Optimality of Logarithmic Investment , 1980, Math. Oper. Res..