English

Neural Ensemble Search via Bayesian Sampling

Machine Learning 2022-06-20 v2

Abstract

Recently, neural architecture search (NAS) has been applied to automate the design of neural networks in real-world applications. A large number of algorithms have been developed to improve the search cost or the performance of the final selected architectures in NAS. Unfortunately, these NAS algorithms aim to select only one single well-performing architecture from their search spaces and thus have overlooked the capability of neural network ensemble (i.e., an ensemble of neural networks with diverse architectures) in achieving improved performance over a single final selected architecture. To this end, we introduce a novel neural ensemble search algorithm, called neural ensemble search via Bayesian sampling (NESBS), to effectively and efficiently select well-performing neural network ensembles from a NAS search space. In our extensive experiments, NESBS algorithm is shown to be able to achieve improved performance over state-of-the-art NAS algorithms while incurring a comparable search cost, thus indicating the superior performance of our NESBS algorithm over these NAS algorithms in practice.

Keywords

Cite

@article{arxiv.2109.02533,
  title  = {Neural Ensemble Search via Bayesian Sampling},
  author = {Yao Shu and Yizhou Chen and Zhongxiang Dai and Bryan Kian Hsiang Low},
  journal= {arXiv preprint arXiv:2109.02533},
  year   = {2022}
}

Comments

Published as a conference paper at UAI 2022

R2 v1 2026-06-24T05:43:18.154Z