LGMLNov 28, 2021

Approximate Inference via Clustering

arXiv:2111.14219v2
Originality Incremental advance
AI Analysis

This addresses computational bottlenecks in Bayesian inference for large datasets, but it is incremental as it builds on existing clustering methods.

The paper tackles the challenge of large-scale Bayesian learning by simplifying the posterior distribution using clustering, showing that the approximate posterior is close to the exact one under certain conditions and is easier to sample from, as validated by experiments.

In recent years, large-scale Bayesian learning draws a great deal of attention. However, in big-data era, the amount of data we face is growing much faster than our ability to deal with it. Fortunately, it is observed that large-scale datasets usually own rich internal structure and is somewhat redundant. In this paper, we attempt to simplify the Bayesian posterior via exploiting this structure. Specifically, we restrict our interest to the so-called well-clustered datasets and construct an \emph{approximate posterior} according to the clustering information. Fortunately, the clustering structure can be efficiently obtained via a particular clustering algorithm. When constructing the approximate posterior, the data points in the same cluster are all replaced by the centroid of the cluster. As a result, the posterior can be significantly simplified. Theoretically, we show that under certain conditions the approximate posterior we construct is close (measured by KL divergence) to the exact posterior. Furthermore, thorough experiments are conducted to validate the fact that the constructed posterior is a good approximation to the true posterior and much easier to sample from.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes