papers AI Learner
The Github is limit! Click to go to the new site.

Parallel Architecture and Hyperparameter Search via Successive Halving and Classification

2018-05-25
Manoj Kumar, George E. Dahl, Vijay Vasudevan, Mohammad Norouzi

Abstract

We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC). The algorithm operates in $K$ stages of parallel function evaluations and trains a cascade of binary classifiers to iteratively cull the undesirable regions of the search space. SHAC is easy to implement, requires no tuning of its own configuration parameters, is invariant to the scale of the objective function and can be built using any choice of binary classifier. We adopt tree-based classifiers within SHAC and achieve competitive performance against several strong baselines for optimizing synthetic functions, hyperparameters and architectures.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1805.10255

PDF

https://arxiv.org/pdf/1805.10255


Similar Posts

Comments