Let’s say β=0.9, c=1/20.
Wouldn’t they have to also magically predict all the stochasticity in the observations, and have a running time that grows exponentially in their log loss?
Oh yeah—that’s good news.
Although I don’t really like to make anything that would fall apart if the world were deterministic. Relying on stochasticity feels wrong to me.
Let’s say β=0.9, c=1/20.
Oh yeah—that’s good news.
Although I don’t really like to make anything that would fall apart if the world were deterministic. Relying on stochasticity feels wrong to me.