# Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions

arXiv: https://arxiv.org/abs/1708.01529 · HTML: https://mlsanity.com/paper/1708.01529/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2017.

## Built on by (most cited first, 8 of 8)

- [Efficient Bayesian Sampling Using Normalizing Flows to Assist Markov Chain Monte Carlo Methods](https://mlsanity.com/paper/2107.08001/) (2021)
- [The Geometry of Neural Nets' Parameter Spaces Under Reparametrization](https://mlsanity.com/paper/2302.07384/) (2023)
- [Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling](https://mlsanity.com/paper/2206.07673/) (2022)
- [Reparameterized Sampling for Generative Adversarial Networks](https://mlsanity.com/paper/2107.00352/) (2021)
- [Tensorizing flows: a tool for variational inference](https://mlsanity.com/paper/2305.02460/) (2023)
- [Variational Rejection Particle Filtering](https://mlsanity.com/paper/2103.15343/) (2021)
- [Learning variational autoencoders via MCMC speed measures](https://mlsanity.com/paper/2308.13731/) (2023)
- [Amortised Inference through One-Step Implicit Sampling](https://mlsanity.com/paper/2610.12679/) (2026)

## Abstract (arXiv)

We introduce a new algorithm for approximate inference that combines reparametrization, Markov chain Monte Carlo and variational methods. We construct a very flexible implicit variational distribution synthesized by an arbitrary Markov chain Monte Carlo operation and a deterministic transformation that can be optimized using the reparametrization trick. Unlike current methods for implicit variational inference, our method avoids the computation of log density ratios and therefore it is easily applicable to arbitrary continuous and differentiable models. We demonstrate the proposed algorithm for fitting banana-shaped distributions and for training variational autoencoders.