Additive regularization schedule for neural architecture search

TL;DR

This paper introduces an additive regularization schedule for neural architecture search, enabling more effective optimization of neural network structures by adaptively adjusting regularizers during training.

Contribution

It proposes a novel method to construct and adaptively schedule additive regularizers in neural architecture search, improving the efficiency and accuracy of the resulting neural networks.

Findings

Regularized models outperform non-regularized ones on multiple datasets.

The method finds neural network structures with lower complexity and high accuracy.

Adaptive regularization scheduling enhances the search process.

Abstract

Neural network structures have a critical impact on the accuracy and stability of forecasting. Neural architecture search procedures help design an optimal neural network according to some loss function, which represents a set of quality criteria. This paper investigates the problem of neural network structure optimization. It proposes a way to construct a loss function, which contains a set of additive elements. Each element is called the regularizer. It corresponds to some part of the neural network structure and represents a criterion to optimize. The optimization procedure changes the structure in iterations. To optimize various parts of the structure, the procedure changes the set of regularizers according to some schedule. The authors propose a way to construct the additive regularization schedule. By comparing regularized models with non-regularized ones for a collection of datasets the computational experiments show that the proposed method finds efficient neural network structure and delivers accurate networks of low complexity.