Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate.

While the joint distribution can be useful (e.g., to learn the distribution

Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate.

These methods implicitly improve the approximate posterior by drawing multiple samples from a proposal, and resampling to discard samples that do not fit the data (Cremer et al.,

In this section, we provide the proofs to the Lemmas which were introduced in the main paper.

Neural Information Processing Systems http://nips.cc/

We would like to thank the reviewers for their kind and thoughtful comments. Any attempt to mitigate particle degeneracy (e.g. Replicating Fig 1BD, we find similar, albeit less extreme results, with TMC always being faster than SMC. In particular, we have included Eq. 36 in the main text, and also included the corresponding choice of This should help to clarify that Eq. 11 applies to any directed graphical model (we have also included references In the example in Figure 1, we consider a model that does not have a chain-structure (see Appendix Figure 1A). IW AE performs arbitrarily badly due to the high-dimensionality of the state-space.