Saved in:
Bibliographic Details
Main Authors: Ranabhat, Nishan, Javanparast, Behnam, Goerz, David, Inack, Estelle
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.07159
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913934875820032
author Ranabhat, Nishan
Javanparast, Behnam
Goerz, David
Inack, Estelle
author_facet Ranabhat, Nishan
Javanparast, Behnam
Goerz, David
Inack, Estelle
contents Portfolio optimization is a routine asset management operation conducted in financial institutions around the world. However, under real-world constraints such as turnover limits and transaction costs, its formulation becomes a mixed-integer nonlinear program that current mixed-integer optimizers often struggle to solve. We propose mapping this problem onto a classical Ising-like Hamiltonian and solving it with Variational Neural Annealing (VNA), via its classical formulation implemented using autoregressive neural networks. We demonstrate that VNA can identify near-optimal solutions for portfolios comprising more than 2,000 assets and yields performance comparable to that of state-of-the-art optimizers, such as Mosek, while exhibiting faster convergence on hard instances. Finally, we present a dynamical finite-size scaling analysis applied to the S&P 500, Russell 1000, and Russell 3000 indices, revealing universal behavior and polynomial annealing time scaling of the VNA algorithm on portfolio optimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_07159
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large-scale portfolio optimization with variational neural annealing
Ranabhat, Nishan
Javanparast, Behnam
Goerz, David
Inack, Estelle
Disordered Systems and Neural Networks
Statistical Mechanics
Machine Learning
Portfolio Management
Portfolio optimization is a routine asset management operation conducted in financial institutions around the world. However, under real-world constraints such as turnover limits and transaction costs, its formulation becomes a mixed-integer nonlinear program that current mixed-integer optimizers often struggle to solve. We propose mapping this problem onto a classical Ising-like Hamiltonian and solving it with Variational Neural Annealing (VNA), via its classical formulation implemented using autoregressive neural networks. We demonstrate that VNA can identify near-optimal solutions for portfolios comprising more than 2,000 assets and yields performance comparable to that of state-of-the-art optimizers, such as Mosek, while exhibiting faster convergence on hard instances. Finally, we present a dynamical finite-size scaling analysis applied to the S&P 500, Russell 1000, and Russell 3000 indices, revealing universal behavior and polynomial annealing time scaling of the VNA algorithm on portfolio optimization problems.
title Large-scale portfolio optimization with variational neural annealing
topic Disordered Systems and Neural Networks
Statistical Mechanics
Machine Learning
Portfolio Management
url https://arxiv.org/abs/2507.07159