Data-informed Deep Optimization
This addresses complex, high-dimensional design problems in scientific and industrial fields, but it appears incremental as it combines existing deep learning techniques for optimization.
The authors tackled high-dimensional design optimization problems where objective functions lack explicit formulas, proposing a data-informed deep optimization (DiDo) approach that uses deep neural networks to learn feasible regions and optimize via gradient descent, yielding good solutions with limited training data in industrial and toy examples.
Complex design problems are common in the scientific and industrial fields. In practice, objective functions or constraints of these problems often do not have explicit formulas, and can be estimated only at a set of sampling points through experiments or simulations. Such optimization problems are especially challenging when design parameters are high-dimensional due to the curse of dimensionality. In this work, we propose a data-informed deep optimization (DiDo) approach as follows: first, we use a deep neural network (DNN) classifier to learn the feasible region; second, we sample feasible points based on the DNN classifier for fitting of the objective function; finally, we find optimal points of the DNN-surrogate optimization problem by gradient descent. To demonstrate the effectiveness of our DiDo approach, we consider a practical design case in industry, in which our approach yields good solutions using limited size of training data. We further use a 100-dimension toy example to show the effectiveness of our model for higher dimensional problems. Our results indicate that the DiDo approach empowered by DNN is flexible and promising for solving general high-dimensional design problems in practice.