Weighted Random Search for CNN Hyperparameter Optimization

Abstract

Nearly all model algorithms used in machine learning use two different sets of parameters: the training parameters and the meta-parameters (hyperparameters). While the training parameters are learned during the training phase, the values of the hyperparameters have to be specified before learning starts. For a given dataset, we would like to find the optimal combination of hyperparameter values, in a reasonable amount of time. This is a challenging task because of its computational complexity. In previous work [11], we introduced the Weighted Random Search (WRS) method, a combination of Random Search (RS) and probabilistic greedy heuristic. In the current paper, we compare the WRS method with several state-of-the art hyperparameter optimization methods with respect to Convolutional Neural Network (CNN) hyperparameter optimization. The criterion is the classification accuracy achieved within the same number of tested combinations of hyperparameter values. According to our experiments, the WRS algorithm outperforms the other methods.

11 pages, 2 figurs, journal article

References in corpus (8)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Neural Architecture Search with Reinforcement Learning
• Neural Architecture Optimization
• Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning
• BayesOpt: A Bayesian Optimization Library for Nonlinear Optimization, Experimental Design and Bandits
• CMA-ES for Hyperparameter Optimization of Deep Neural Networks
• FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
• Big Holes in Big Data: A Monte Carlo Algorithm for Detecting Large Hyper-rectangles in High Dimensional Data

Cited by in corpus (1)

• Bayesian Hyperparameter Optimization for Deep Neural Network-Based Network Intrusion Detection