### Abstract

We consider an online learning framework where the task is to predict a permutation which represents a ranking of n fixed objects. At each trial, the learner incurs a loss defined as Kendall tau distance between the predicted permutation and the true permutation given by the adversary. This setting is quite natural in many situations such as information retrieval and recommendation tasks. We prove a lower bound of the cumulative loss and hardness results. Then, we propose an algorithm for this problem and prove its relative loss bound which shows our algorithm is close to optimal.

Original language | English |
---|---|

Pages (from-to) | 539-553 |

Number of pages | 15 |

Journal | Journal of Machine Learning Research |

Volume | 25 |

Publication status | Published - Dec 1 2012 |

Event | 4th Asian Conference on Machine Learning, ACML 2012 - Singapore, Singapore Duration: Nov 4 2012 → Nov 6 2012 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Software
- Control and Systems Engineering
- Statistics and Probability
- Artificial Intelligence

### Cite this

*Journal of Machine Learning Research*,

*25*, 539-553.

**Online rank aggregation.** / Yasutake, Shota; hatano, kohei; Takimoto, Eiji; Takeda, Masayuki.

Research output: Contribution to journal › Conference article

*Journal of Machine Learning Research*, vol. 25, pp. 539-553.

}

TY - JOUR

T1 - Online rank aggregation

AU - Yasutake, Shota

AU - hatano, kohei

AU - Takimoto, Eiji

AU - Takeda, Masayuki

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We consider an online learning framework where the task is to predict a permutation which represents a ranking of n fixed objects. At each trial, the learner incurs a loss defined as Kendall tau distance between the predicted permutation and the true permutation given by the adversary. This setting is quite natural in many situations such as information retrieval and recommendation tasks. We prove a lower bound of the cumulative loss and hardness results. Then, we propose an algorithm for this problem and prove its relative loss bound which shows our algorithm is close to optimal.

AB - We consider an online learning framework where the task is to predict a permutation which represents a ranking of n fixed objects. At each trial, the learner incurs a loss defined as Kendall tau distance between the predicted permutation and the true permutation given by the adversary. This setting is quite natural in many situations such as information retrieval and recommendation tasks. We prove a lower bound of the cumulative loss and hardness results. Then, we propose an algorithm for this problem and prove its relative loss bound which shows our algorithm is close to optimal.

UR - http://www.scopus.com/inward/record.url?scp=84876844002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876844002&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84876844002

VL - 25

SP - 539

EP - 553

JO - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

SN - 1532-4435

ER -