DEEP-BO for Hyperparameter Optimization of Deep Networks
arXiv:1905.09680
Abstract
The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly affected when a technique like batchnorm is used. As a result, hyperparameter optimization of deep networks can be much more challenging than traditional machine learning models. In this work, we start from well known Bayesian Optimization solutions and provide enhancement strategies specifically designed for hyperparameter optimization of deep networks. The resulting algorithm is named as DEEP-BO (Diversified, Early-termination-Enabled, and Parallel Bayesian Optimization). When evaluated over six DNN benchmarks, DEEP-BO easily outperforms or shows comparable performance with some of the well-known solutions including GP-Hedge, Hyperband, BOHB, Median Stopping Rule, and Learning Curve Extrapolation. The code used is made publicly available at https://github.com/snu-adsl/DEEP-BO.
26 pages, NeurIPS19 under review
References in corpus (6)
- Practical Bayesian Optimization of Machine Learning Algorithms
- Batch Bayesian Optimization via Local Penalization
- Batched Large-scale Bayesian Optimization in High-dimensional Spaces
- Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions
- Batched Gaussian Process Bandit Optimization via Determinantal Point Processes
- TAPAS: Train-less Accuracy Predictor for Architecture Search