[lostmsu]

There was a recent paper from Uber, that GA works well for weights, so I wouldn't drop that area right away.

[oteytaud]

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.

[lostmsu]

Doesn't the model Uber used begin with a bunch of convolutional layer sets, since it processes raw images?

[mi_lk]

What’s GA here?

[oteytaud]

GA stands for genetic algorithms.