k*-Nearest Neighbors: From Global to Local

Authors: Oren Anava, Kfir Levy

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

Reproducibility Variable Result LLM Response
Research Type Experimental Section 4 Experimental Results, The following experiments demonstrate the effectiveness of the proposed algorithm on several datasets. In our experiments we use 8 real-world datasets, Table 1: Experimental results.
Researcher Affiliation Collaboration Oren Anava The Voleon Group oren@voleon.com, Kfir Y. Levy ETH Zurich yehuda.levy@inf.eth.ch
Pseudocode Yes Algorithm 1 k-NN
Open Source Code No The paper does not contain any explicit statements about releasing source code or links to a repository for the described methodology.
Open Datasets Yes In our experiments we use 8 real-world datasets, all are available in the UCI repository website (https://archive.ics.uci.edu/ml/).
Dataset Splits Yes We randomly divide each dataset into two halves (one used for validation and the other for test). On the first half (the validation set), we run the two baselines and our algorithm with different values of k, σ and L/C (respectively), using 5-fold cross validation.
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies (library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes Specifically, we consider values of k in {1, 2, . . . , 10} and values of σ and L/C in {0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1, 5, 10}.