swMATH ID: 41118
Software Authors: Lakhmiri, Dounia; Digabel, Sébastien Le; Tribes, Christophe
Description: HyperNOMAD is a C++ and Python package dedicated to the hyperparameter optimization of deep neural networks. The package contains a blackbox specifically designed for this problematic and provides a link with the NOMAD software used for the optimization. The blackbox takes as inputs a list of hyperparameters, builds a corresponding deep neural network in order to train, validate and test it on a specific data set before returning the test error as a mesure of performance. NOMAD is then used to minimize this error. The following appendix provides an overview of how to use the HyperNOMAD package.
Homepage: https://arxiv.org/abs/1907.01698
Source Code: https://github.com/bbopt/HyperNOMAD
Dependencies: C++; Python
Keywords: deep neural networks; blackbox optimization; categorical variables; derivative-free optimization; hyperparameter optimization; mesh adaptive direct search; neural architecture search
Related Software: NOMAD; Scikit; Hyperband; Fashion-MNIST; GitHub; PyTorch; MNIST; DeepHyper; Adam; Optuna; scikit-optimize; RBFOpt; MISO; STL-10 dataset; Hyperopt; CIFAR; APPSPACK; BFO; MOE; RMSprop
Cited in: 5 Publications

Citations by Year