one feedback talking to a few researchers and showing the design is that the optim API right now doesn't allow one to optimize a non parameter variable.
For example, when optimizing like neural-art maybe, but also a bunch of meta-optimization research (like learning to learning to learn).
We should consider making it optional to give model in the constructor, and allow .step to take in params to optimize
one feedback talking to a few researchers and showing the design is that the optim API right now doesn't allow one to optimize a non parameter variable.
For example, when optimizing like neural-art maybe, but also a bunch of meta-optimization research (like learning to learning to learn).
We should consider making it optional to give model in the constructor, and allow .step to take in params to optimize