Variance is concave, so portfolio risk must be too.

The mean-variance model employs quadratic programming to optimize (minimize) portfolio risk. My understanding is that quadratic programming requires a convex objective function. So if the objective function in portfolio optimization is concave, how can it be solved with a routine that requires a convex one?

Below are my guesses:

- Portfolio risk is in fact convex somehow due to it being
*weighted*variance - It complies to the optimizer because it is not variance, but a positive-definite covariance matrix, that satisfies the convexity requirement

Quantitative Finance Asked on December 4, 2020

2 AnswersFirst, a correction is in order: the math question you cite is the variance for a Bernoulli random variable as a function of the parameter $p$. That is, indeed, concave in $p$. However, the variance of a portfolio, $w^TSigma w$, is *not* concave in $w$. So your initial presumption of concavity is not correct.

For a Bernoulli random variable, the uncertainty of outcomes is most uncertain for outcomes that are equally likely. That is very different from a portfolio where weights of $1/N$ diversify our exposure to multiple sources of risk and thus tend to reduce the total variance.

For a mean-variance portfolio optimization, we have the following problem: $$ begin{align} max_w &~w^T R - frac{lambda}{2} w^TSigma w \ text{s.t.} &~||w||_1 = 1. end{align} $$

Here, the objective function is a linear function minus a quadratic form; that is concave.

If we instead use a coherent measure of risk, the objective function just becomes $w^T R - frac{lambda}{2} text{Risk}(w)$. Note that coherent risk measures (like CVaR/ES/TCE/ETL) are convex as discussed in Föllmer and Schied (2008).

Both of these objectives are concave. However, as Arshdeep's existing answer notes, a concave function can be made convex by multiplying by -1. Finally I should note that we do not even need convexity but often merely quasi-convexity (which might be the case for constrained optimizations).

Correct answer by kurtosis on December 4, 2020

I'm in no way a portfolio theory expert, but the negative of a convex function is concave and vice versa. You can look at minimizing a concave function as maximizing a convex function and vice versa.

Also, the optimization problem is over the weights, and not over densities (which variance is concave in as your link shows). Portfolio variance is convex in the weights.

Answered by Arshdeep Singh Duggal on December 4, 2020

1 Asked on March 11, 2021 by lithium123

2 Asked on March 2, 2021 by dickybrown

1 Asked on February 25, 2021

garch high frequency high frequency estimators variance volatility

0 Asked on February 16, 2021 by wei-wu

1 Asked on February 10, 2021

1 Asked on February 9, 2021 by user144410

1 Asked on February 8, 2021 by tsz-chun-leung

2 Asked on February 8, 2021 by user51725

0 Asked on February 8, 2021 by browl

0 Asked on February 5, 2021

1 Asked on February 4, 2021 by rc76

0 Asked on February 3, 2021 by vivek-subramanian

3 Asked on January 25, 2021 by user330060

3 Asked on January 23, 2021 by dirtside

5 Asked on January 20, 2021 by dordal

0 Asked on January 17, 2021 by ffbzona

0 Asked on January 15, 2021 by user49942

1 Asked on January 7, 2021 by user45980

Get help from others!

Recent Questions

Recent Answers

- cdvel on Nano syntax highlighting for Debian
- Elliott Slaughter on Runing a command without inheriting parent’s environment
- BloodyIron on dual monitor ubuntu issue
- user1686 on Runing a command without inheriting parent’s environment
- barti_ddu on Nano syntax highlighting for Debian

© 2021 InsideDarkWeb.com. All rights reserved.