Salvato in:
Dettagli Bibliografici
Autori principali: Cummins, James S., Berloff, Natalia G.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.06566
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912113249746944
author Cummins, James S.
Berloff, Natalia G.
author_facet Cummins, James S.
Berloff, Natalia G.
contents Portfolio optimization is a ubiquitous problem in financial mathematics that relies on accurate estimates of covariance matrices for asset returns. However, estimates of pairwise covariance could be better and calculating time-sensitive optimal portfolios is energy-intensive for digital computers. We present an energy-efficient, fast, and fully analog pipeline for solving portfolio optimization problems that overcomes these limitations. The analog paradigm leverages the fundamental principles of physics to recover accurate optimal portfolios in a two-step process. Firstly, we utilize equilibrium propagation, an analog alternative to backpropagation, to train linear autoencoder neural networks to calculate low-rank covariance matrices. Then, analog continuous Hopfield networks output the minimum variance portfolio for a given desired expected return. The entire efficient frontier may then be recovered, and an optimal portfolio selected based on risk appetite.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06566
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Fully Analog Pipeline for Portfolio Optimization
Cummins, James S.
Berloff, Natalia G.
Portfolio Management
Disordered Systems and Neural Networks
Computational Engineering, Finance, and Science
Optics
Quantum Physics
Portfolio optimization is a ubiquitous problem in financial mathematics that relies on accurate estimates of covariance matrices for asset returns. However, estimates of pairwise covariance could be better and calculating time-sensitive optimal portfolios is energy-intensive for digital computers. We present an energy-efficient, fast, and fully analog pipeline for solving portfolio optimization problems that overcomes these limitations. The analog paradigm leverages the fundamental principles of physics to recover accurate optimal portfolios in a two-step process. Firstly, we utilize equilibrium propagation, an analog alternative to backpropagation, to train linear autoencoder neural networks to calculate low-rank covariance matrices. Then, analog continuous Hopfield networks output the minimum variance portfolio for a given desired expected return. The entire efficient frontier may then be recovered, and an optimal portfolio selected based on risk appetite.
title A Fully Analog Pipeline for Portfolio Optimization
topic Portfolio Management
Disordered Systems and Neural Networks
Computational Engineering, Finance, and Science
Optics
Quantum Physics
url https://arxiv.org/abs/2411.06566