oteytaud

... incidentally Hyperopt has the advantage of considering conditional domains; we might either do the same or combine Nevergrad with Hyperopt...

For property-based testing I would say yes, with an objective function equal to the margin by which the properties are satisfied.

Program synthesis only in some particular cases, like the parametrization of programs for speed or another criterion - but not in the general case of program synthesis.

For small numbers of hyperparameters, sometimes just random search is enough. This is not an absolute rule, sometimes with just 4 parameters random search miserably fails... just my rule of thumb, empirically, is that for hyperparameters in machine learning (this is certainly not the case in general) random search is often enough for 4 to 12 hyperparameters if the budget for hyperparameter search is ~100 trainings.

Sure GA can be great for weights as well - but mainly when gradient is unreliable. I would not use Nevergrad for training the weights of a convolutional network for image classification for example; whereas I use Nevergrad for WorldModels.

GA stands for genetic algorithms.

We have not yet released examples of interfaces with Pytorch. Maybe with moderate number of hyperparameters the benefit compared to random search will be moderate, whereas it will be very significant with high number of hyperparameters. It also depends on how parallel you are. In all cases we have a wide range of algorithms with a common interface, so that you can compare.

We also use it for direct training of the weights of a network in reinforcement learning, not only hyperparameters.

We have a wide range of experiments on plenty of objective functions in games, reinforcement learning, in real world design and machine learning hyperparameter tuning - these reports will come soon.

To the best of my knowledge, Hyperopt is limited to random search and Parzen variants. We have more algorithms, and include test functions, deal with noise. On the other hand, in Hyperopt conditional variables are naturally handled, whereas for the moment Nevergrad needs user manual work on this. Both frameworks are asynchronous.

To the best of my knowledge, Hyperopt is limited to random search and Parzen variants. We have more algorithms, and include test functions, deal with noise. On the other hand, in Hyperopt conditional variables are naturally handled, whereas for the moment Nevergrad needs user manual work on this.

Both frameworks are asynchronous.

It's black-box optimization. This means that we just have an objective function, without access to derivatives or whatever other information. This is not relevant for training weights in deep learning for image classification, or other things for which the gradient works well.