This is a collection of useful Hyperparameter Tuning Methods.
- general
- review
- gridsearch
- random search
- Bayesian optimization
- Evolutionary optimization
- Population-based optimization
- reinforcement learning
[A Visual Exploration of Gaussian Processes]
[An Intro to Hyper-parameter Optimization using Grid Search and Random Search]
[Comparing parameter tuning methods for evolutionary algorithms]
[Random Search for Hyper-Parameter Optimization]
[A Tutorial on Bayesian Optimization]
[A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning]
[A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise] POI
[Efficient Global Optimization of Expensive Black-Box Functions] EI
[Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design] UCB
[Predictive Entropy Search for Efficient Global Optimization of Black-box Functions] Entropy
[Batch Bayesian Optimization via Local Penalization]
[BOHB: Robust and Efficient Hyperparameter Optimization at Scale]
[LEARNING CURVE PREDICTION WITH BAYESIAN NEURAL NETWORKS]
[Scalable Bayesian Optimization Using Deep Neural Networks]
[Evolutionary optimization: A review and implementation of several algorithms]
[Recent advances in differential evolution – An updated survey]
[Differential Evolution (DE) for Continuous Function Optimization]
[Population Based Training of Neural Networks]
[Hyp-RL : Hyperparameter Optimization by Reinforcement Learning]
[Neural Architecture Search with Reinforcement Learning]
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent