Parameter Optimization with Conscious Allocation (POCA)
This work addresses the computational efficiency of hyperparameter tuning for machine learning practitioners, but it is incremental as it builds on existing hyperband-based approaches.
The paper tackles the problem of hyperparameter optimization in machine learning by introducing POCA, a hyperband-based algorithm that adaptively allocates computational budget using Bayesian sampling, resulting in faster discovery of strong configurations compared to its nearest competitor in tests on a toy function and a deep neural network.
The performance of modern machine learning algorithms depends upon the selection of a set of hyperparameters. Common examples of hyperparameters are learning rate and the number of layers in a dense neural network. Auto-ML is a branch of optimization that has produced important contributions in this area. Within Auto-ML, hyperband-based approaches, which eliminate poorly-performing configurations after evaluating them at low budgets, are among the most effective. However, the performance of these algorithms strongly depends on how effectively they allocate the computational budget to various hyperparameter configurations. We present the new Parameter Optimization with Conscious Allocation (POCA), a hyperband-based algorithm that adaptively allocates the inputted budget to the hyperparameter configurations it generates following a Bayesian sampling scheme. We compare POCA to its nearest competitor at optimizing the hyperparameters of an artificial toy function and a deep neural network and find that POCA finds strong configurations faster in both settings.