14. Duben 2021
Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used to estimate gradients of expectations throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks, with no insight into their nature. We use a first principles approach to explain that LR and RP are alternative methods of keeping track of the movement of probability mass, and the two are connected via the divergence theorem. Moreover, we show that the space of all possible estimators combining LR and RP can be completely parameterized by a flow field u(x) and importance sampling distribution q(x). We prove that there cannot exist a single-sample estimator of this type outside our characterized space, thus, clarifying where we should be searching for better Monte Carlo gradient estimators.
The 24th International Conference on Artificial Intelligence and Statistics was held virtually from Tuesday, 13 April 2021 to Thursday, 15 April 2021.
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Prezentace na podobné téma, kategorii nebo přednášejícího