# Bayesian Neural Architecture Search using A Training-Free Performance Metric

arXiv: https://arxiv.org/abs/2001.10726 · HTML: https://mlsanity.com/paper/2001.10726/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2020.

## Built on by (most cited first, 9 of 9)

- [Learning Deep Morphological Networks with Neural Architecture Search](https://mlsanity.com/paper/2106.07714/) (2021)
- [An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters](https://mlsanity.com/paper/2303.12797/) (2023)
- [Fitness Landscape Footprint: A Framework to Compare Neural Architecture Search Problems](https://mlsanity.com/paper/2111.01584/) (2021)
- [A Comprehensive Survey on Automated Machine Learning for Recommendations](https://mlsanity.com/paper/2204.01390/) (2022)
- [A Data-driven Approach to Neural Architecture Search Initialization](https://mlsanity.com/paper/2111.03524/) (2021)
- [Lessons from the Clustering Analysis of a Search Space: A Centroid-based Approach to Initializing NAS](https://mlsanity.com/paper/2108.09126/) (2021)
- [Landscape of Neural Architecture Search across sensors: how much do they differ ?](https://mlsanity.com/paper/2201.06321/) (2022)
- [Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning](https://mlsanity.com/paper/2202.01958/) (2022)
- [Bayesian Optimization in Sequence-to-Architecture Latent Space for Zero-Shot NAS](https://mlsanity.com/paper/2610.06167/) (2026)

## Abstract (arXiv)

Recurrent neural networks (RNNs) are a powerful approach for time series prediction. However, their performance is strongly affected by their architecture and hyperparameter settings. The architecture optimization of RNNs is a time-consuming task, where the search space is typically a mixture of real, integer and categorical values. To allow for shrinking and expanding the size of the network, the representation of architectures often has a variable length. In this paper, we propose to tackle the architecture optimization problem with a variant of the Bayesian Optimization (BO) algorithm. To reduce the evaluation time of candidate architectures the Mean Absolute Error Random Sampling (MRS), a training-free method to estimate the network performance, is adopted as the objective function for BO. Also, we propose three fixed-length encoding schemes to cope with the variable-length architecture representation. The result is a new perspective on accurate and efficient design of RNNs, that we validate on three problems. Our findings show that 1) the BO algorithm can explore different network architectures using the proposed encoding schemes and successfully designs well-performing architectures, and 2) the optimization time is significantly reduced by using MRS, without compromising the performance as compared to the architectures obtained from the actual training procedure.