Mean Variance Optimization

Mean-variance optimization (MVO) aims to find the optimal balance between maximizing expected returns and minimizing risk in investment portfolios or similar decision-making problems. Current research focuses on improving MVO's accuracy and efficiency by incorporating machine learning techniques, such as deep reinforcement learning and decision-focused learning, to better estimate uncertain parameters and handle complex, multi-stage decision processes within Markov Decision Processes (MDPs). These advancements address limitations of traditional MVO approaches, particularly in handling risk aversion and incorporating factors like ESG considerations. The resulting improvements have significant implications for portfolio management, resource allocation, and other fields requiring robust decision-making under uncertainty.

Papers

September 15, 2024

Anatomy of Machines for Markowitz: Decision-Focused Learning for Mean-Variance Portfolio Optimization
Junhyeong Lee, Inwoo Tae, Yongjae Lee
LeArning Abstract New Machine Portfolio Selection Stock Return Prediction Decision Focused Learning Variance Portfolio Mean Variance Optimization

June 12, 2024

Finite Time Analysis of Temporal Difference Learning for Mean-Variance in a Discounted MDP
Tejaram Sangadi, L. A. Prashanth, Krishna Jagannathan
Markov Decision Process Actor Critic Algorithm Linear Function Approximation Temporal Difference Learning Finite Time Risk Sensitive Reinforcement Learning Markov Reward Process Mean Variance Optimization

March 25, 2024

Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization
Fernando Acero, Parisa Zehtabi, Nicolas Marchesotti, Michael Cashmore, Daniele Magazzeni, Manuela Veloso
Deep Reinforcement Learning Portfolio Optimization Mean Variance Optimization Responsible Portfolio

February 27, 2023

Global Algorithms for Mean-Variance Optimization in Markov Decision Processes
Li Xia, Shuai Ma
Markov Decision Process Bilevel Optimization Infinite Horizon Mean Variance Optimization

February 13, 2022

Deep Reinforcement Learning and Convex Mean-Variance Optimisation for Portfolio Management
Ruan Pretorius, Terence van Zyl
Deep Reinforcement Learning Portfolio Management Classical Optimization Portfolio Optimization Model Investment Strategy Mean Variance Optimization

January 29, 2022

Learning Stochastic Graph Neural Networks with Constrained Variance
Zhan Gao, Elvin Isufi
Primal Dual Constrained Learning Stochastic Network Mean Variance Optimization

January 15, 2022

A unified algorithm framework for mean-variance optimization in discounted Markov decision processes
Shuai Ma, Xiaoteng Ma, Li Xia
Markov Decision Process Value Iteration Risk Averse Unified Algorithm Mean Variance Optimization

Mean Variance Optimization

Papers

Anatomy of Machines for Markowitz: Decision-Focused Learning for Mean-Variance Portfolio Optimization

Finite Time Analysis of Temporal Difference Learning for Mean-Variance in a Discounted MDP

Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization

Global Algorithms for Mean-Variance Optimization in Markov Decision Processes

Deep Reinforcement Learning and Convex Mean-Variance Optimisation for Portfolio Management

Learning Stochastic Graph Neural Networks with Constrained Variance

A unified algorithm framework for mean-variance optimization in discounted Markov decision processes