FlashFolio: A GPU-Accelerated Solver for Portfolio Optimization

TL;DR

FlashFolio is a GPU-accelerated solver that significantly speeds up large-scale portfolio optimization, making complex multi-period models more practical.

Contribution

It introduces a GPU-based solver that outperforms traditional solvers like MOSEK in speed and robustness for portfolio optimization tasks.

Findings

Achieves up to 12.9x speedup in single-period optimization.

Achieves up to 48x speedup in multi-period optimization.

Demonstrates improved robustness on challenging instances.

Abstract

We present FlashFolio, a GPU-accelerated solver for single-period and multi-period portfolio optimization with factor-based risk modeling, bid-offer spread costs, and nonlinear market impact. These models are widely used in portfolio construction and optimal execution, but become computationally challenging at large scale, especially in the multi-period setting. We benchmark FlashFolio against MOSEK on instances constructed from realistic market inputs. FlashFolio delivers consistent runtime improvements, achieving speedups of up to 12.9x in the single-period setting and 48x in the multi-period setting, while also exhibiting stronger robustness on challenging multi-period instances. Our results show that GPU-based optimization can help improve the practicality of large-scale portfolio optimization.