5

LightGBM Parameter Optimization with Optuna

Previous chapters have discussed the LightGBM hyperparameters and their effect on building models. A fundamental problem when building a new model is finding the optimal hyperparameters to achieve the best performance.

This chapter focuses on the parameter optimization process using a framework called Optuna. Different optimization algorithms are discussed alongside the pruning of the hyperparameter space. A practical example shows how to apply Optuna to find optimal parameters for LightGBM. Advanced use cases for Optuna are also shown.

The chapter’s main topics are as follows:

  • Optuna and optimization algorithms
  • Optimizing LightGBM with Optuna

Technical requirements

The chapter includes examples ...

Get Machine Learning with LightGBM and Python now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.