Nevergrad: A Python library for performing derivative-free ML optimization
1–10 of 28 posts
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#2How does this compare to hyperopt?
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#3I'm still waiting for a bogograd optimizer!
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#4isn't this the same thing as blackbox learning?
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#5Has anyone tried this? Interested to know if results were in line with the benchmarks.
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#6isn't this the same thing as blackbox learning?
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.
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#7To 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.
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#8How does this compare to hyperopt?
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.
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#9Has anyone tried this? Interested to know if results were in line with the benchmarks.
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.
Re: Nevergrad: A Python library for performing derivative-free ML optimization
#10isn't this the same thing as blackbox learning?
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.
There was a recent paper from Uber, that GA works well for weights, so I wouldn't drop that area right away.