MARS: Meta-Learning as Score Matching in the Function Space. (arXiv:2210.13319v1 [cs.LG])

Meta-learning aims to extract useful inductive biases from a set of related
datasets. In Bayesian meta-learning, this is typically achieved by constructing
a prior distribution over neural network parameters. However, specifying
families of computationally viable prior distributions over the
high-dimensional neural network parameters is difficult. As a result, existing
approaches resort to meta-learning restrictive diagonal Gaussian priors,
severely limiting their expressiveness and performance. To circumvent these
issues, we approach meta-learning through the lens of functional Bayesian
neural network inference, which …

arxiv function mars meta meta-learning space