|
| 投资组合的一个序列凸近似算法 |
| A sequential convex approximation algorithm for portfolio optimization model |
| 投稿时间：2016-07-04 修订日期：2016-08-22 |
| DOI： |
| 中文关键词: 投资组合 序列凸近似 凸优化 Monte-Carlo方法 |
| 英文关键词: portfolio optimization sequential convex Approximation Monte-Carlo method |
| 基金项目: |
|
| 摘要点击次数: 196 |
| 全文下载次数: 0 |
| 中文摘要: |
| 目前以CVaR 为代表的凸优化投资组合模型 引起了广泛研究。本文试图克服传统的投资组合模型中凸近似的不足，提出了一个投资组合的DC规划模型。
该模型用一个DC函数替代了 CVaR 模型中的凸近似函数，同时要求所有约束条件在概率意义下成立。
本文提出一个序列凸近似(SCA)算法求解所提出的DC规划问题，并运用Monte Carlo 方法来实现 SCA 算法。
初步的实验结果表明，因子收益 服从 “尖峰厚尾”分布时，模型的目标函数值优于采用CVaR概率近似的目标函数值。 |
| 英文摘要: |
| CVaR has received extensive attentions as a representative convex portfolio model in recent years. This paper aims to overcome the limits of convex approximations for traditional portfolio models and proposes a DC programming for portfolio. In the proposed programming, a DC function is proposed as a surrogate for the convex approximation function in the CVaR model. All the constraints are satisfied in the probabilistic sense in the DC programming. Moreover, a sequential convex approximation (SCA) algorithm is designed to solve the DC programming. The SCA algorithm is implemented by employing Monte-Carlo method. Preliminary experimental results have shown that the objective function values of the DC programming are better than those with CVaR approximation when the income factors have ``fat tail' distributions. |
|
View Fulltext
查看/发表评论 下载PDF阅读器 |
| 关闭 |