Query Complexity of k-NN based Mode Estimation
Authors:
- 11 April 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Motivated by the mode estimation problem of an unknown multivariate probability density function, we study the problem of identifying the point with the minimum k-th nearest neighbor distance for a given dataset of n points. We study the case where the pairwise distances are apriori unknown, but we have access to an oracle which we can query to get noisy information about the distance between any pair of points. For two natural oracle models, we design a sequential learning algorithm, based on the idea of confidence intervals, which adaptively decides which queries to send to the oracle and is able to correctly solve the problem with high probability. We derive instance-dependent upper bounds on the query complexity of our proposed scheme and also demonstrate significant improvement over the performance of other baselines via extensive numerical evaluations.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Bandit Algorithms2020
- The Modal Age of StatisticsInternational Statistical Review, 2020
- Nonparametric modal regressionThe Annals of Statistics, 2016
- A comprehensive approach to mode clusteringElectronic Journal of Statistics, 2016
- Best-arm identification algorithms for multi-armed bandits in the fixed confidence setting2014