Learning from small samples: An analysis of simple decision heuristics

Özgür Şimşek, Marcus Buckmann

Research output: Chapter in Book/Report/Conference proceedingChapter

  • 2 Citations

Abstract

Simple decision heuristics are models of human and animal behavior that use few pieces of information---perhaps only a single piece of information---and integrate the pieces in simple ways, for example, by considering them sequentially, one at a time, or by giving them equal weight. It is unknown how quickly these heuristics can be learned from experience. We show, analytically and empirically, that only a few training samples lead to substantial progress in learning. We focus on three families of heuristics: single-cue decision making, lexicographic decision making, and tallying. Our empirical analysis is the most extensive to date, employing 63 natural data sets on diverse subjects.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 28 (NIPS 2015): Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, December 7-12, 2015
EditorsC. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, R. Garnett
PublisherCurran Associates, Inc.
Pages3159-3167
Number of pages9
StatePublished - 2015

Fingerprint

Heuristics
Small sample
Animals

Cite this

Şimşek, Ö., & Buckmann, M. (2015). Learning from small samples: An analysis of simple decision heuristics. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 28 (NIPS 2015): Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, December 7-12, 2015 (pp. 3159-3167). Curran Associates, Inc..

Learning from small samples: An analysis of simple decision heuristics. / Şimşek, Özgür; Buckmann, Marcus.

Advances in Neural Information Processing Systems 28 (NIPS 2015): Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, December 7-12, 2015. ed. / C. Cortes; N. D. Lawrence; D. D. Lee; M. Sugiyama; R. Garnett. Curran Associates, Inc., 2015. p. 3159-3167.

Research output: Chapter in Book/Report/Conference proceedingChapter

Şimşek, Ö & Buckmann, M 2015, Learning from small samples: An analysis of simple decision heuristics. in C Cortes, ND Lawrence, DD Lee, M Sugiyama & R Garnett (eds), Advances in Neural Information Processing Systems 28 (NIPS 2015): Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, December 7-12, 2015. Curran Associates, Inc., pp. 3159-3167.
Şimşek Ö, Buckmann M. Learning from small samples: An analysis of simple decision heuristics. In Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R, editors, Advances in Neural Information Processing Systems 28 (NIPS 2015): Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, December 7-12, 2015. Curran Associates, Inc.2015. p. 3159-3167.

Şimşek, Özgür; Buckmann, Marcus / Learning from small samples: An analysis of simple decision heuristics.

Advances in Neural Information Processing Systems 28 (NIPS 2015): Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, December 7-12, 2015. ed. / C. Cortes; N. D. Lawrence; D. D. Lee; M. Sugiyama; R. Garnett. Curran Associates, Inc., 2015. p. 3159-3167.

Research output: Chapter in Book/Report/Conference proceedingChapter

@inbook{bad574225de84c57828b5c85a6356dfa,
title = "Learning from small samples: An analysis of simple decision heuristics",
abstract = "Simple decision heuristics are models of human and animal behavior that use few pieces of information---perhaps only a single piece of information---and integrate the pieces in simple ways, for example, by considering them sequentially, one at a time, or by giving them equal weight. It is unknown how quickly these heuristics can be learned from experience. We show, analytically and empirically, that only a few training samples lead to substantial progress in learning. We focus on three families of heuristics: single-cue decision making, lexicographic decision making, and tallying. Our empirical analysis is the most extensive to date, employing 63 natural data sets on diverse subjects.",
author = "Özgür Şimşek and Marcus Buckmann",
year = "2015",
pages = "3159--3167",
editor = "C. Cortes and Lawrence, {N. D.} and Lee, {D. D.} and M. Sugiyama and R. Garnett",
booktitle = "Advances in Neural Information Processing Systems 28 (NIPS 2015): Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, December 7-12, 2015",
publisher = "Curran Associates, Inc.",
address = "USA United States",

}

TY - CHAP

T1 - Learning from small samples: An analysis of simple decision heuristics

AU - Şimşek,Özgür

AU - Buckmann,Marcus

PY - 2015

Y1 - 2015

N2 - Simple decision heuristics are models of human and animal behavior that use few pieces of information---perhaps only a single piece of information---and integrate the pieces in simple ways, for example, by considering them sequentially, one at a time, or by giving them equal weight. It is unknown how quickly these heuristics can be learned from experience. We show, analytically and empirically, that only a few training samples lead to substantial progress in learning. We focus on three families of heuristics: single-cue decision making, lexicographic decision making, and tallying. Our empirical analysis is the most extensive to date, employing 63 natural data sets on diverse subjects.

AB - Simple decision heuristics are models of human and animal behavior that use few pieces of information---perhaps only a single piece of information---and integrate the pieces in simple ways, for example, by considering them sequentially, one at a time, or by giving them equal weight. It is unknown how quickly these heuristics can be learned from experience. We show, analytically and empirically, that only a few training samples lead to substantial progress in learning. We focus on three families of heuristics: single-cue decision making, lexicographic decision making, and tallying. Our empirical analysis is the most extensive to date, employing 63 natural data sets on diverse subjects.

UR - http://papers.nips.cc/paper/5643-learning-from-small-samples-an-analysis-of-simple-decision-heuristics

M3 - Chapter

SP - 3159

EP - 3167

BT - Advances in Neural Information Processing Systems 28 (NIPS 2015): Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, December 7-12, 2015

PB - Curran Associates, Inc.

ER -