Accelerating Neural Architecture Search using Performance Prediction

by   Bowen Baker, et al.

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.


page 1

page 2

page 3

page 4


ACE: Adaptive Constraint-aware Early Stopping in Hyperparameter Optimization

Deploying machine learning models requires high model quality and needs ...

Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search

Reliable yet efficient evaluation of generalisation performance of a pro...

Neural Predictor for Neural Architecture Search

Neural Architecture Search methods are effective but often use complex a...

Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting

Early stopping based on the validation set performance is a popular appr...

Use of static surrogates in hyperparameter optimization

Optimizing the hyperparameters and architecture of a neural network is a...

Learning to Rank Learning Curves

Many automated machine learning methods, such as those for hyperparamete...

Model Agnostic Conformal Hyperparameter Optimization

Several novel frameworks for hyperparameter search have emerged in the l...

Please sign up or login with your details

Forgot password? Click here to reset