Near-optimal sample compression for nearest neighbors

Lee Ad Gottlieb; Aryeh Kontorovich; Pinhas Nisnevitch

Near-optimal sample compression for nearest neighbors

Lee Ad Gottlieb, Aryeh Kontorovich, Pinhas Nisnevitch

Ariel University, Ben-Gurion University of the Negev

Research output: Contribution to journal › Conference article › peer-review

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 language	English
Pages (from-to)	370-378
Number of pages	9
Journal	Advances in Neural Information Processing Systems
Volume	1
Issue number	January
State	Published - 1 Jan 2014
Event	28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada Duration: 8 Dec 2014 → 13 Dec 2014

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@article{d8b35ceb8fc34a7680594e433eebdbb9,

title = "Near-optimal sample compression for nearest neighbors",

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.",

author = "Gottlieb, \{Lee Ad\} and Aryeh Kontorovich and Pinhas Nisnevitch",

year = "2014",

month = jan,

day = "1",

language = "الإنجليزيّة",

volume = "1",

pages = "370--378",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

number = "January",

note = "28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 ; Conference date: 08-12-2014 Through 13-12-2014",

}

TY - JOUR

T1 - Near-optimal sample compression for nearest neighbors

AU - Gottlieb, Lee Ad

AU - Kontorovich, Aryeh

AU - Nisnevitch, Pinhas

PY - 2014/1/1

Y1 - 2014/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84937956771&partnerID=8YFLogxK

M3 - مقالة من مؤنمر

SN - 1049-5258

VL - 1

SP - 370

EP - 378

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

IS - January

T2 - 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014

Y2 - 8 December 2014 through 13 December 2014

ER -

Near-optimal sample compression for nearest neighbors

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this