# Accelerated Parallel Non-conjugate Sampling for Bayesian Non-parametric Models

## TL;DR

This paper introduces a novel accelerated parallel MCMC method for Bayesian nonparametric latent feature models, improving inference speed and convergence by data-driven feature proposals and parallelization.

## Contribution

It presents a new data-driven feature proposal mechanism and an approximate parallel inference strategy, enhancing efficiency and scalability of Bayesian nonparametric models.

## Key findings

- Accelerated mixing of latent variable inference.
- Parallel inference significantly reduces computation time.
- Method achieves quick convergence to posterior.

## Abstract

Inference of latent feature models in the Bayesian nonparametric setting is generally difficult, especially in high dimensional settings, because it usually requires proposing features from some prior distribution. In special cases, where the integration is tractable, we can sample new feature assignments according to a predictive likelihood. We present a novel method to accelerate the mixing of latent variable model inference by proposing feature locations based on the data, as opposed to the prior. First, we introduce an accelerated feature proposal mechanism that we show is a valid MCMC algorithm for posterior inference. Next, we propose an approximate inference strategy to perform accelerated inference in parallel. A two-stage algorithm that combines the two approaches provides a computationally attractive method that can quickly reach local convergence to the posterior distribution of our model, while allowing us to exploit parallelization.