DeepAI AI Chat
Log In Sign Up

The Theory and Algorithm of Ergodic Inference

by   Yichuan Zhang, et al.

Approximate inference algorithm is one of the fundamental research fields in machine learning. The two dominant theoretical inference frameworks in machine learning are variational inference (VI) and Markov chain Monte Carlo (MCMC). However, because of the fundamental limitation in the theory, it is very challenging to improve existing VI and MCMC methods on both the computational scalability and statistical efficiency. To overcome this obstacle, we propose a new theoretical inference framework called ergodic Inference based on the fundamental property of ergodic transformations. The key contribution of this work is to establish the theoretical foundation of ergodic inference for the development of practical algorithms in future work.


page 1

page 2

page 3

page 4


MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference

In this contribution, we propose a new computationally efficient method ...

Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions

We introduce a new algorithm for approximate inference that combines rep...

Orbital MCMC

Markov Chain Monte Carlo (MCMC) is a computational approach to fundament...

Variational inference via Wasserstein gradient flows

Along with Markov chain Monte Carlo (MCMC) methods, variational inferenc...

Deep Fiducial Inference

Since the mid-2000s, there has been a resurrection of interest in modern...

MCMC Algorithms for Posteriors on Matrix Spaces

We study Markov chain Monte Carlo (MCMC) algorithms for target distribut...

Instant Replay: Investigating statistical Analysis in Sports

Technology has had an unquestionable impact on the way people watch spor...