CMA-ES for Hyperparameter Optimization of Deep Neural Networks
Hyperparameters of deep neural networks are often optimized by grid search, random search or Bayesian optimization. As an alternative, we propose to use the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), which is known for its state-of-the-art performance in derivative-free optimization. CMA-ES has some useful invariance properties and is friendly to parallel evaluations of solutions. We provide a toy example comparing CMA-ES and state-of-the-art Bayesian optimization algorithms for tuning the hyperparameters of a convolutional neural network for the MNIST dataset on 30 GPUs in parallel.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimizationHyperparameter OptimizationSimilar Papers 제목 키워드 기반
Stochastic Hyperparameter Optimization through Hypernetworks
Machine learning models are often tuned by nesting optimization of model weights inside the optimization of hyperparameters. We give a method to collapse this nested optimization into joint stochastic optimization of wei…
BIG-bench Machine LearningHyperparameter OptimizationStochastic OptimizationOptimizing Large-Scale Hyperparameters via Automated Learning Algorithm
Modern machine learning algorithms usually involve tuning multiple (from one to thousands) hyperparameters which play a pivotal role in terms of model generalizability. Black-box optimization and gradient-based algorithm…
Hyperparameter OptimizationDP-HyPO: An Adaptive Private Hyperparameter Optimization Framework
Hyperparameter optimization, also known as hyperparameter tuning, is a widely recognized technique for improving model performance. Regrettably, when training private ML models, many practitioners often overlook the priv…
Hyperparameter OptimizationPrivacy PreservingBayesian Hyperparameter Optimization with BoTorch, GPyTorch and Ax
Deep learning models are full of hyperparameters, which are set manually before the learning process can start. To find the best configuration for these hyperparameters in such a high dimensional space, with time-consumi…
Bayesian OptimizationGaussian ProcessesGraph ClassificationHyperparameter OptimizationDP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization
Hyperparameter optimization, also known as hyperparameter tuning, is a widely recognized technique for improving model performance. Regrettably, when training private ML models, many practitioners often overlook the priv…