A hypothesis class admits a sample compression scheme, if for every samp...
Score matching is an alternative to maximum likelihood (ML) for estimati...
A classical result in learning theory shows the equivalence of PAC
learn...
Noise Contrastive Estimation (NCE) is a popular approach for learning
pr...
Normalizing flows are a widely used class of latent-variable generative
...
Probabilistic inference in pairwise Markov Random Fields (MRFs), i.e.
co...
In this paper, we consider the problem of learning functions over sets, ...