# Accelerating Neural Architecture Search using Performance Prediction

arXiv: https://arxiv.org/abs/1705.10823 · HTML: https://mlsanity.com/paper/1705.10823/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2017.

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

- [Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale](https://mlsanity.com/paper/2201.06834/) (2022)
- [PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2204.12726/) (2022)
- [NAAP-440 Dataset and Baseline for Neural Architecture Accuracy Prediction](https://mlsanity.com/paper/2209.06626/) (2022)
- [EmProx: Neural Network Performance Estimation For Neural Architecture Search](https://mlsanity.com/paper/2206.05972/) (2022)
- [Accuracy Prediction for NAS Acceleration using Feature Selection and Extrapolation](https://mlsanity.com/paper/2211.12419/) (2022)
- [FlexHB: a More Efficient and Flexible Framework for Hyperparameter Optimization](https://mlsanity.com/paper/2402.13641/) (2024)
- [Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns](https://mlsanity.com/paper/2605.07378/) (2026)
- [When does a network's training history predict its future learning better than its current state? Evidence from a response probe and a forecasting screen](https://mlsanity.com/paper/2610.09621/) (2026)
- [Language Models as AI Research World Models](https://mlsanity.com/paper/2610.12235/) (2026)

## Abstract (arXiv)

Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations. In this paper, we show that standard frequentist regression models can predict the final performance of partially trained model configurations using features based on network architectures, hyperparameters, and time-series validation performance data. We empirically show that our performance prediction models are much more effective than prominent Bayesian counterparts, are simpler to implement, and are faster to train. Our models can predict final performance in both visual classification and language modeling domains, are effective for predicting performance of drastically varying model architectures, and can even generalize between model classes. Using these prediction models, we also propose an early stopping method for hyperparameter optimization and meta-modeling, which obtains a speedup of a factor up to 6x in both hyperparameter optimization and meta-modeling. Finally, we empirically show that our early stopping method can be seamlessly incorporated into both reinforcement learning-based architecture selection algorithms and bandit based search methods. Through extensive experimentation, we empirically show our performance prediction models and early stopping algorithm are state-of-the-art in terms of prediction accuracy and speedup achieved while still identifying the optimal model configurations.