Variational Weighting for Kernel Density Ratios

Sangwoong Yoon, F. Park, Gunsu S Yun, Iljung Kim, Yung-Kyun Noh
2/12/2026

No official code found. Best implementation: swyoon/variationally-weighted-kernel-density-estimation (5 stars, MIT, last commit 2023-11-11).

Abstract

Kernel density estimation (KDE) is integral to a range of generative and discriminative tasks in machine learning. Drawing upon tools from the multidimensional calculus of variations, we derive an optimal weight function that reduces bias in standard kernel density estimates for density ratios, leading to improved estimates of prediction posteriors and information-theoretic measures. In the process, we shed light on some fundamental aspects of density estimation, particularly from the perspective of algorithms that employ KDEs as their main building blocks.

View on arXivView PDF

Code Implementations(1)

swyoon/variationally-weighted-kernel-density-estimationCommunity100%
MIT
52PythonOct 27, 20232 years agoMIT

Similar Papers

On Kernel-based Variational Autoencoder

81% match2024

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization

81% match1 repo22024

Kernel Density Machines

80% match2025

Kernel Semi-Implicit Variational Inference

80% match1 repo92026

Tracking Dynamic Gaussian Density with a Theoretically Optimal Sliding Window Approach

79% match2024

SD-KDE: Score-Debiased Kernel Density Estimation

79% match2025

Cite this paper

@article{yoon2026variational,
  title  = {Variational Weighting for Kernel Density Ratios},
  author = {Sangwoong Yoon and F. Park and Gunsu S Yun and Iljung Kim and Yung-Kyun Noh},
  year   = {2026},
  eprint = {2311.03001},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2311.03001},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.03001.svg)](https://codeofpaper.com/paper/2311.03001)

Discussion