This paper presents a tutorial introduction to the use of variational methods for inference and learning in graphical models (Bayesian networks and Markov random fields), and describes a general framework for generating variational transformations based on convex duality.Expand

A natural way of achieving this combination by deriving kernel functions for use in discriminative methods such as support vector machines from generative probability models is developed.Expand

This paper proposes a method that leverages refined alignment of latent representations to perform style transfer on the basis of non-parallel text, and demonstrates the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.Expand

A novel approach to collaborative prediction is presented, using low-norm instead of low-rank factorizations, inspired by, and has strong connections to, large-margin linear discrimination.Expand

The junction tree variational autoencoder generates molecular graphs in two phases, by first generating a tree-structured scaffold over chemical substructures, and then combining them into a molecule with a graph message passing network, which allows for incrementally expand molecules while maintaining chemical validity at every step.Expand

This work develops and analyze methods for computing provably optimal maximum a posteriori probability (MAP) configurations for a subclass of Markov random fields defined on graphs with cycles and establishes a connection between a certain LP relaxation of the mode-finding problem and a reweighted form of the max-product (min-sum) message-passing algorithm.Expand

This paper proposes an alternative inference method for additive factorial hidden Markov models, an extension to HMMs where the state factors into multiple independent chains, and the output is an additive function of all the hidden states.Expand

A novel message passing algorithm for approximating the MAP problem in graphical models that is derived via block coordinate descent in a dual of the LP relaxation of MAP, but does not require any tunable parameters such as step size or tree weights.Expand

A new class of upper bounds on the log partition function of a Markov random field (MRF) is introduced, based on concepts from convex duality and information geometry, and the Legendre mapping between exponential and mean parameters is exploited.Expand