On the Consistency of Quick Shift

Authors: Heinrich Jiang

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove that Quick Shift recovers the modes of an arbitrary multimodal density at a minimax optimal rate under mild nonparametric assumptions. This provides an alternative to known procedures with similar statistical guarantees; however such procedures only recover the modes but fail to inform us how to assign the sample points to a mode which is critical for clustering. Quick Shift on the other hand recovers both the modes and the clustering assignments with statistical consistency guarantees. Moreover, Quick Shift s ability to do all of this has been extensively validated in practice.
Researcher Affiliation Industry Heinrich Jiang Google Inc. 1600 Amphitheatre Parkway, Mountain View, CA 94043 heinrich.jiang@gmail.com
Pseudocode Yes Algorithm 1 Quick Shift; Algorithm 2 Quick Shift Cluster Tree Estimator; Algorithm 3 Quick Shift Modal Regression
Open Source Code No The paper does not provide any specific links or explicit statements about the release of source code for the described methodology.
Open Datasets No The paper focuses on theoretical consistency guarantees and does not report on experiments using a specific, publicly available dataset that requires access information.
Dataset Splits No The paper focuses on theoretical consistency guarantees and does not describe experimental data splits (train, validation, test) for reproducibility.
Hardware Specification No The paper is theoretical and does not report on empirical experiments. Therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not report on empirical experiments that would require specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not report on empirical experiments that would require detailed experimental setup parameters like hyperparameters or training configurations.