528491

Thanks for pointing that out. The current implementation is not self-adapting the parameters (like mutation strength) of the individuals in the population: https://github.com/SimonBlanke/Gradient-Free-Optimizers/issu...

The title was to long, but I edited my comment for clarification. Hyperparameter optimization is normally done with gradient-free-optimization techniques, since a gradient cannot be computed. This is opposed to the optimization of parameters during training (e.g. neural network weights).

The new release adds the Genetic Algorithm and Differential Evolution. Also check out the documentation for the new optimization algorithms: https://simonblanke.github.io/gradient-free-optimizers-docum...

This new release adds multiple small new features/changes. Among them is the early-stopping feature for optimization strategies, which enables to chain together optimization algorithms in more interesting ways. See the tutorial page for some examples: https://simonblanke.github.io/hyperactive-documentation/4.5/...

This new version adds the DIRECT optimizer