[pchiusano]

You might like these posts on gradient free optimization:

http://pchiusano.github.io/2019-07-06/learning-without-a-gra...

http://pchiusano.github.io/2020-10-12/learning-without-a-gra...

I think you’re right that the area is underexplored.

[eismcc]

Has anyone tried using another NN as the “gradient” function? With the hope of making it less “blind?”

[rolisz]

DeepMind has a thing called synthetic gradients: https://www.deepmind.com/blog/decoupled-neural-interfaces-us....