Near-optimal sample compression for nearest neighbors

Lee Ad Gottlieb, Aryeh Kontorovich, Pinhas Nisnevitch

Research output: Contribution to journalConference articlepeer-review

18 Scopus citations

Abstract

We present the first sample compression algorithm for nearest neighbors with non-trivial performance guarantees. We complement these guarantees by demonstrating almost matching hardness lower bounds, which show that our bound is nearly optimal. Our result yields new insight into margin-based nearest neighbor classification in metric spaces and allows us to significantly sharpen and simplify existing bounds. Some encouraging empirical results are also presented.

Original languageEnglish
Pages (from-to)370-378
Number of pages9
JournalAdvances in Neural Information Processing Systems
Volume1
Issue numberJanuary
StatePublished - 1 Jan 2014
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: 8 Dec 201413 Dec 2014

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Near-optimal sample compression for nearest neighbors'. Together they form a unique fingerprint.

Cite this