3 papers
cs.LG2020
Woodbury Transformations for Deep Generative Flows
You Lu, Bert Huang
Normalizing flows are deep generative models that allow efficient likelihood calculation and sampling. The core requirement for this advantage is that they are constructed using fu…
cs.LG2019
Structured Output Learning with Conditional Generative Flows
You Lu, Bert Huang
Traditional structured prediction models try to learn the conditional likelihood, i.e., p(y|x), to capture the relationship between the structured output y and the input features x…
cs.LG2018
Block Belief Propagation for Parameter Learning in Markov Random Fields
You Lu, Zhiyuan Liu, Bert Huang
Traditional learning methods for training Markov random fields require doing inference over all variables to compute the likelihood gradient. The iteration complexity for those met…