Learning the Efficient Frontier

TL;DR

NeuralEF is a neural network-based framework that efficiently approximates the efficient frontier in resource allocation problems, significantly speeding up large-scale simulations and handling complex constraints.

Contribution

It introduces NeuralEF, a novel neural approximation method that reformulates the efficient frontier optimization as a sequence-to-sequence problem for faster computation.

Findings

NeuralEF accurately forecasts EF solutions across various constraints.

It accelerates large-scale simulations of resource allocation.

The method handles discontinuous behaviors effectively.

Abstract

The efficient frontier (EF) is a fundamental resource allocation problem where one has to find an optimal portfolio maximizing a reward at a given level of risk. This optimal solution is traditionally found by solving a convex optimization problem. In this paper, we introduce NeuralEF: a fast neural approximation framework that robustly forecasts the result of the EF convex optimization problem with respect to heterogeneous linear constraints and variable number of optimization inputs. By reformulating an optimization problem as a sequence to sequence problem, we show that NeuralEF is a viable solution to accelerate large-scale simulation while handling discontinuous behavior.