Viewing profile — 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, l…

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 m…

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 classific…

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 …

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 repor…

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 H…

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 H…

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 weig…