Hyperparameter Optimization

Hyperparameter Optimization is the problem of choosing a set of optimal hyperparameters for a learning algorithm. Whether the algorithm is suitable for the data directly depends on hyperparameters, which directly influence overfitting or underfitting. Each model requires different assumptions, weights or training speeds for different types of data under the conditions of a given loss function. Source: Data-driven model for fracturing design optimization: focus on building digital database and production forecast

Benchmarks

Libraries

Datasets

Subtasks

Most implemented papers

Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization

Content

A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning

Optuna: A Next-generation Hyperparameter Optimization Framework

Are GANs Created Equal? A Large-Scale Study

Optimizing Millions of Hyperparameters by Implicit Differentiation

A Tutorial on Bayesian Optimization

Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks

A System for Massively Parallel Hyperparameter Tuning

Single Headed Attention RNN: Stop Thinking With Your Head

MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements