Regret bounds for online portfolio selection with a cardinality constraint

Shinji Ito, Daisuke Hatano, Hanna Sumita, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken Ichi Kawarabayashi

Research output: Contribution to journalConference article

Abstract

Online portfolio selection is a sequential decision-making problem in which a learner repetitively selects a portfolio over a set of assets, aiming to maximize long-term return. In this paper, we study the problem with the cardinality constraint that the number of assets in a portfolio is restricted to be at most k, and consider two scenarios: (i) in the full-feedback setting, the learner can observe price relatives (rates of return to cost) for all assets, and (ii) in the bandit-feedback setting, the learner can observe price relatives only for invested assets. We propose efficient algorithms for these scenarios, which achieve sublinear regrets. We also provide regret (statistical) lower bounds for both scenarios which nearly match the upper bounds when k is a constant. In addition, we give a computational lower bound, which implies that no algorithm maintains both computational efficiency, as well as a small regret upper bound.

Original languageEnglish
Pages (from-to)10588-10597
Number of pages10
JournalAdvances in Neural Information Processing Systems
Volume2018-December
Publication statusPublished - 2018 Jan 1
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: 2018 Dec 22018 Dec 8

Fingerprint

Feedback
Computational efficiency
Decision making
Costs

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Ito, S., Hatano, D., Sumita, H., Yabe, A., Fukunaga, T., Kakimura, N., & Kawarabayashi, K. I. (2018). Regret bounds for online portfolio selection with a cardinality constraint. Advances in Neural Information Processing Systems, 2018-December, 10588-10597.

Regret bounds for online portfolio selection with a cardinality constraint. / Ito, Shinji; Hatano, Daisuke; Sumita, Hanna; Yabe, Akihiro; Fukunaga, Takuro; Kakimura, Naonori; Kawarabayashi, Ken Ichi.

In: Advances in Neural Information Processing Systems, Vol. 2018-December, 01.01.2018, p. 10588-10597.

Research output: Contribution to journalConference article

Ito, S, Hatano, D, Sumita, H, Yabe, A, Fukunaga, T, Kakimura, N & Kawarabayashi, KI 2018, 'Regret bounds for online portfolio selection with a cardinality constraint', Advances in Neural Information Processing Systems, vol. 2018-December, pp. 10588-10597.
Ito S, Hatano D, Sumita H, Yabe A, Fukunaga T, Kakimura N et al. Regret bounds for online portfolio selection with a cardinality constraint. Advances in Neural Information Processing Systems. 2018 Jan 1;2018-December:10588-10597.
Ito, Shinji ; Hatano, Daisuke ; Sumita, Hanna ; Yabe, Akihiro ; Fukunaga, Takuro ; Kakimura, Naonori ; Kawarabayashi, Ken Ichi. / Regret bounds for online portfolio selection with a cardinality constraint. In: Advances in Neural Information Processing Systems. 2018 ; Vol. 2018-December. pp. 10588-10597.
@article{50d66182d8a24f9da2c10d9164caac6f,
title = "Regret bounds for online portfolio selection with a cardinality constraint",
abstract = "Online portfolio selection is a sequential decision-making problem in which a learner repetitively selects a portfolio over a set of assets, aiming to maximize long-term return. In this paper, we study the problem with the cardinality constraint that the number of assets in a portfolio is restricted to be at most k, and consider two scenarios: (i) in the full-feedback setting, the learner can observe price relatives (rates of return to cost) for all assets, and (ii) in the bandit-feedback setting, the learner can observe price relatives only for invested assets. We propose efficient algorithms for these scenarios, which achieve sublinear regrets. We also provide regret (statistical) lower bounds for both scenarios which nearly match the upper bounds when k is a constant. In addition, we give a computational lower bound, which implies that no algorithm maintains both computational efficiency, as well as a small regret upper bound.",
author = "Shinji Ito and Daisuke Hatano and Hanna Sumita and Akihiro Yabe and Takuro Fukunaga and Naonori Kakimura and Kawarabayashi, {Ken Ichi}",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "2018-December",
pages = "10588--10597",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

TY - JOUR

T1 - Regret bounds for online portfolio selection with a cardinality constraint

AU - Ito, Shinji

AU - Hatano, Daisuke

AU - Sumita, Hanna

AU - Yabe, Akihiro

AU - Fukunaga, Takuro

AU - Kakimura, Naonori

AU - Kawarabayashi, Ken Ichi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Online portfolio selection is a sequential decision-making problem in which a learner repetitively selects a portfolio over a set of assets, aiming to maximize long-term return. In this paper, we study the problem with the cardinality constraint that the number of assets in a portfolio is restricted to be at most k, and consider two scenarios: (i) in the full-feedback setting, the learner can observe price relatives (rates of return to cost) for all assets, and (ii) in the bandit-feedback setting, the learner can observe price relatives only for invested assets. We propose efficient algorithms for these scenarios, which achieve sublinear regrets. We also provide regret (statistical) lower bounds for both scenarios which nearly match the upper bounds when k is a constant. In addition, we give a computational lower bound, which implies that no algorithm maintains both computational efficiency, as well as a small regret upper bound.

AB - Online portfolio selection is a sequential decision-making problem in which a learner repetitively selects a portfolio over a set of assets, aiming to maximize long-term return. In this paper, we study the problem with the cardinality constraint that the number of assets in a portfolio is restricted to be at most k, and consider two scenarios: (i) in the full-feedback setting, the learner can observe price relatives (rates of return to cost) for all assets, and (ii) in the bandit-feedback setting, the learner can observe price relatives only for invested assets. We propose efficient algorithms for these scenarios, which achieve sublinear regrets. We also provide regret (statistical) lower bounds for both scenarios which nearly match the upper bounds when k is a constant. In addition, we give a computational lower bound, which implies that no algorithm maintains both computational efficiency, as well as a small regret upper bound.

UR - http://www.scopus.com/inward/record.url?scp=85064812908&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064812908&partnerID=8YFLogxK

M3 - Conference article

VL - 2018-December

SP - 10588

EP - 10597

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -