Closed JisuHann closed 2 years ago
a continuous function satisfies Properties 1,2(Permutation-invariant, Translation Equivariance) if and only if it has a representation of the form
ex. we often observe only one (possibly multi-dimensional) observation per input location, which corresponds to multiplicity one.
a function is continuous, permutation invariant and translation equivariant if and only if it has a representation of the form
for some continuous and translation-equivariant \rho and some continuous \phi and \psi , where H is an appropriate space of functions that include the image of E. We call a function \Phii of the above form CONVDEEPSET.
Neural Process
CNP: Conditional Neural Processes(ICML2018)
define conditional distributions over functions given a set of observations
Advantage
On classification task
LNP: (Latent) Neural Processes(ICML2018)
GP, DNN, Meta-learning