An effective algorithm for hyperparameter optimization of neural networks
This addresses the time-consuming process of hyperparameter tuning for neural networks, offering an automated solution that is incremental in improving efficiency.
The paper tackles the challenge of manually tuning neural network hyperparameters by formulating it as a box-constrained optimization problem and applying a derivative-free tool that uses radial basis function models to accelerate the search for high-accuracy configurations, showing promising results on benchmark sets and drug-drug interaction prediction.
A major challenge in designing neural network (NN) systems is to determine the best structure and parameters for the network given the data for the machine learning problem at hand. Examples of parameters are the number of layers and nodes, the learning rates, and the dropout rates. Typically, these parameters are chosen based on heuristic rules and manually fine-tuned, which may be very time-consuming, because evaluating the performance of a single parametrization of the NN may require several hours. This paper addresses the problem of choosing appropriate parameters for the NN by formulating it as a box-constrained mathematical optimization problem, and applying a derivative-free optimization tool that automatically and effectively searches the parameter space. The optimization tool employs a radial basis function model of the objective function (the prediction accuracy of the NN) to accelerate the discovery of configurations yielding high accuracy. Candidate configurations explored by the algorithm are trained to a small number of epochs, and only the most promising candidates receive full training. The performance of the proposed methodology is assessed on benchmark sets and in the context of predicting drug-drug interactions, showing promising results. The optimization tool used in this paper is open-source.