We introduce Score identity Distillation (SiD), an innovative data-free method that distills the
generative capabilities of pretrained diffusion models into a single-step generator. SiD not …

Semi-implicit variational inference (SIVI) has been introduced to expand the analytical
variational families by defining expressive semi-implicit distributions in a hierarchical …

Semi-implicit variational inference (SIVI) greatly enriches the expressiveness of variational
families by considering implicit variational distributions defined in a hierarchical manner …

Semi-implicit variational inference (SIVI) extends traditional variational families with semi-
implicit distributions defined in a hierarchical manner. Due to the intractable densities of …

In many machine learning tasks, input features with varying degrees of predictive capability
are acquired at varying costs. In order to optimize the performance-cost trade-off, one would …

We propose a novel approach to perform approximate Bayesian inference in complex
models such as Bayesian neural networks. The approach is more scalable to large data …

Bayesian uncertainty quantification is the key element to many machine learning
applications. To this end, approximate inference algorithms are developed to perform …

Mean-field variational inference (VI) is computationally scalable, but its highly-demanding
independence requirement hinders it from being applied to wider scenarios. Although many …

Over the past decade variational inference (VI) has surpassed Markov Chain Monte Carlo
(MCMC) as the main method for performing scalable parametric Bayesian inference …