Maximum Margin Multiclass Nearest Neighbors

Authors: Aryeh Kontorovich, Roi Weiss

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We develop a general framework for marginbased multicategory classification in metric spaces. The basic work-horse is a marginregularized version of the nearest-neighbor classifier. We prove generalization bounds that match the state of the art in sample size n and significantly improve the dependence on the number of classes k.
Researcher Affiliation Academia Aryeh Kontorovich KARYEH@CS.BGU.AC.IL Department of Computer Science, Ben-Gurion University, Beer Sheva 84105, ISRAEL Roi Weiss ROIWEI@CS.BGU.AC.IL Department of Computer Science, Ben-Gurion University, Beer Sheva 84105, ISRAEL
Pseudocode No The paper describes algorithmic steps and procedures in text (e.g., in Section 4 'Algorithm') but does not include any formally labeled pseudocode blocks or algorithms.
Open Source Code No The paper does not provide any statements or links indicating the availability of open-source code for the described methodology.
Open Datasets No This is a theoretical paper that focuses on mathematical proofs and algorithmic analysis. It does not use or refer to any specific publicly available datasets for training or evaluation.
Dataset Splits No This is a theoretical paper and does not involve experimental validation on datasets, thus no training, validation, or test splits are described.
Hardware Specification No This is a theoretical paper and does not report on conducted experiments, therefore no hardware specifications are mentioned.
Software Dependencies No This is a theoretical paper and does not involve software implementation details, therefore no specific software dependencies or versions are mentioned.
Experiment Setup No This is a theoretical paper and does not report on conducted experiments, therefore no experimental setup details, hyperparameters, or training configurations are provided.