Learning the Efficient Frontier
This work provides a faster solution for portfolio optimization in finance, though it is incremental as it applies an existing neural method to a known bottleneck.
The paper tackles the efficient frontier resource allocation problem by introducing NeuralEF, a neural approximation framework that forecasts the results of convex optimization with heterogeneous constraints, achieving a 10x speedup in simulations while handling discontinuous behavior.
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.