Training Deep Generative Models: Variations on a Theme

By Philip Bachman. 2015

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

Citations in the corpus

Energy-Inspired Models: Learning with Sampler-Induced Distributions (2019, background): “1 under mild conditions [9]. as Bachman and Precup [3] introduced the idea of viewing IWAE auxiliary variable variational inference and Naesseth et al. [51], Cremer et al. [13], Domke and Sheldon [20] formalized the notion.”
Inference Suboptimality in Variational Autoencoders (2018, methodology): “As shown by Bachman & Precup (2015) and Cremer et al. (2017), the IWAE bound can be seen as using the VAE bound but with an importance weighted q distribution.”
Importance Weighting and Variational Inference (2018, background): “Previous work has connected IWVI and NIS by showing that the importance weighted ELBO is a lower bound of the ELBO applied to the NIS distribution [6, 16, 2].”
Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation (2019, background): “Several recent works have viewed Monte Carlo VI bounds through the lens of augmented VI [3, 10, 20, 11, 16].”
Z-Forcing: Training Stochastic Recurrent Networks (2017, background): “…the approximate posterior may loosely match the true posterior and the IWAE bound can correct for this mismatch by tightening the posterior approximation, i.e. the IWAE bound can be interpreted as the standard VAE lower bound with an implicit posterior distribution (Bachman and Precup, 2015).”
Reinterpreting Importance-Weighted Autoencoders (2017, background): “Bachman & Precup (2015) also showed that the IWAE objective is equivalent to stochastic variational inference with a proposal distribution corrected towards the true posterior via normalized importance sampling.”