# AutoML: A Survey of the State-of-the-Art

## TL;DR

This paper provides a comprehensive review of AutoML, focusing on neural architecture search and its recent advancements, challenges, and future directions in automating deep learning system development.

## Contribution

It offers an up-to-date survey of AutoML methods, especially NAS, including performance comparisons and discussion of emerging research directions.

## Key findings

- Summarizes NAS algorithms' performance on CIFAR-10 and ImageNet.
- Highlights promising directions like one-shot NAS and joint optimization.
- Discusses open problems and future research challenges in AutoML.

## Abstract

Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering the applications of DL to more areas. Automated machine learning (AutoML) becomes a promising solution to build a DL system without human assistance, and a growing number of researchers focus on AutoML. In this paper, we provide a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. First, we introduce AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS). We focus more on NAS, as it is currently very hot sub-topic of AutoML. We summarize the performance of the representative NAS algorithms on the CIFAR-10 and ImageNet datasets and further discuss several worthy studying directions of NAS methods: one/two-stage NAS, one-shot NAS, and joint hyperparameter and architecture optimization. Finally, we discuss some open problems of the existing AutoML methods for future research.