Finite-Sample Analysis of Fixed-k Nearest Neighbor Density Functional Estimators

Authors: Shashank Singh, Barnabas Poczos

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We provide finite-sample analysis of a general framework for using k-nearest neighbor statistics to estimate functionals of a nonparametric continuous probability density, including entropies and divergences. Rather than plugging a consistent density estimate (which requires k as the sample size n ) into the functional of interest, the estimators we consider fix k and perform a bias correction. This is more efficient computationally, and, as we show in certain cases, statistically, leading to faster convergence rates. Our framework unifies several previous estimators, for most of which ours are the first finite sample guarantees.
Researcher Affiliation Academia Shashank Singh Statistics & Machine Learning Departments Carnegie Mellon University sss1@andrew.cmu.edu Barnabás Póczos Machine Learning Departments Carnegie Mellon University bapoczos@cs.cmu.edu
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper refers to the ITE toolbox, which contains MATLAB code for the estimators being analyzed, but this is a third-party resource ([48] by Zoltán Szabó) and not code released by the authors specifically for the analytical framework described in this paper.
Open Datasets No The paper is theoretical and does not use datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not describe training, validation, or test dataset splits.
Hardware Specification No The paper does not specify any hardware used for experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers for its theoretical work.
Experiment Setup No The paper is theoretical and does not describe an experimental setup or hyperparameters.