(Un)Conditional Sample Generation Based on Distribution Element Trees

TL;DR

This paper introduces a method leveraging distribution element trees (DETs) for efficient unconditional and conditional random sample generation, enhancing density estimation and sampling flexibility.

Contribution

It presents a novel approach to generate samples using DETs, enabling both unconditional and conditional sampling without significant computational overhead.

Findings

Samples generated are similar to smooth bootstrap methods.

Conditional sampling is straightforward with DETs.

The approach is computationally efficient.

Abstract

Recently, distribution element trees (DETs) were introduced as an accurate and computationally efficient method for density estimation. In this work, we demonstrate that the DET formulation promotes an easy and inexpensive way to generate random samples similar to a smooth bootstrap. These samples can be generated unconditionally, but also, without further complications, conditionally utilizing available information about certain probability-space components.