Partial concepts are functions that can be undefined in certain parts of the input space.

Sampling is an important research problem in statistics learning with many applications such as Bayesian inference [1], multi-arm bandit optimization [2], and reinforcement learning [3].

Sampling is an important research problem in statistics learning with many applications such as Bayesian inference [1], multi-arm bandit optimization [2], and reinforcement learning [3].

Fine-grained zero-shot learning task requires some form of side-information to transfer discriminative information from seen to unseen classes.

For decades, the dominant paradigm for approximate Bayesian inferencep(z|x) = p(z,x)/p(x) has been Markov-Chain Monte-Carlo (MCMC) algorithms, which estimate the evidencep(x) = R p(z,x)dz via sampling. However, since sampling tends to be a slow and computationally intensive process, these sampling-based approximate inference methods fadewhendealing withthemodern probabilistic machine learning problems that usually involveverycomplexmodels, high-dimensional feature spaces andlargedatasets.