You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
The objective function isn't always known e.g. GANs. RL problems also involve objectives that can only be sampled from. I get the local vs global argument, but it's unclear what you mean about backprop being limited by objectives.
"known" objective doesn't mean "can be expressed analytically as a func of the data", it means you know what you're optimizing for from the start. Your GAN implementation itself is an expression of a known optimization objective. "Unknown objective" refers to open-ended problems.
As for sampling -- that can only work if your objective space has a structure that can be easily embedded in a continuous space. Basically why deep RL doesn't work
Saying "deep RL doesn't work" is an excessively broad claim. The fact that the value function of Go can be embedded in this way makes me question the significant of this difficulty.
So that would imply this isn't a backprop problem, but rather a problem with optimization as a field? Could you give an example of an "open ended problem"
With GANs, you know what the end product is going to be: a model that has learned the latent distribution of your data and that you can sample from. You can train multiple GANs and get approximately the same results. So you know B and you know how to get from A to B
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
