### Abstract

The development in information technology has resulted in more diverse data characteristics and a larger data scale. Therefore, pattern recognition techniques have received significant interest in various fields. In this study, we focus on a pattern recognition technique based on distance metric learning, which is known as the learning method in metric matrix under an arbitrary constraint from the training data. This method can acquire the distance structure, which takes account of the statistical characteristics of the training data. Most distance metric learning methods estimate the metric matrix from pairs of training data. One of the problem of the distance metric learning is that the computational complexity for prediction (i. e. distance calculation) is relatively high especially when the dimension of input data becomes large. To calculate the distance effectively, we propose the way to derive low rank metric matrix with nuclear norm regularization. When solving the optimization problem, we use the alternating direction method of multiplier and proximal gradient. To verify the effectiveness of our proposed method from the viewpoint of classification accuracy and rank reduction, simulation experiments using benchmark data sets are conducted.

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

Title of host publication | 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings |

Publisher | Institute of Electrical and Electronics Engineers Inc. |

Pages | 1-5 |

Number of pages | 5 |

Volume | 2018-January |

ISBN (Electronic) | 9781538627259 |

DOIs | |

Publication status | Published - 2018 Feb 2 |

Event | 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Honolulu, United States Duration: 2017 Nov 27 → 2017 Dec 1 |

### Other

Other | 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 |
---|---|

Country | United States |

City | Honolulu |

Period | 17/11/27 → 17/12/1 |

### Fingerprint

### ASJC Scopus subject areas

- Artificial Intelligence
- Computer Science Applications
- Control and Optimization

### Cite this

*2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings*(Vol. 2018-January, pp. 1-5). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI.2017.8280952

**Distance metric learning using each category centroid with nuclear norm regularization.** / Mikawa, Kenta; Kobayashi, Manabu; Goto, Masayuki; Hirasawa, Shigeichi.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings.*vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017, Honolulu, United States, 17/11/27. https://doi.org/10.1109/SSCI.2017.8280952

}

TY - GEN

T1 - Distance metric learning using each category centroid with nuclear norm regularization

AU - Mikawa, Kenta

AU - Kobayashi, Manabu

AU - Goto, Masayuki

AU - Hirasawa, Shigeichi

PY - 2018/2/2

Y1 - 2018/2/2

N2 - The development in information technology has resulted in more diverse data characteristics and a larger data scale. Therefore, pattern recognition techniques have received significant interest in various fields. In this study, we focus on a pattern recognition technique based on distance metric learning, which is known as the learning method in metric matrix under an arbitrary constraint from the training data. This method can acquire the distance structure, which takes account of the statistical characteristics of the training data. Most distance metric learning methods estimate the metric matrix from pairs of training data. One of the problem of the distance metric learning is that the computational complexity for prediction (i. e. distance calculation) is relatively high especially when the dimension of input data becomes large. To calculate the distance effectively, we propose the way to derive low rank metric matrix with nuclear norm regularization. When solving the optimization problem, we use the alternating direction method of multiplier and proximal gradient. To verify the effectiveness of our proposed method from the viewpoint of classification accuracy and rank reduction, simulation experiments using benchmark data sets are conducted.

AB - The development in information technology has resulted in more diverse data characteristics and a larger data scale. Therefore, pattern recognition techniques have received significant interest in various fields. In this study, we focus on a pattern recognition technique based on distance metric learning, which is known as the learning method in metric matrix under an arbitrary constraint from the training data. This method can acquire the distance structure, which takes account of the statistical characteristics of the training data. Most distance metric learning methods estimate the metric matrix from pairs of training data. One of the problem of the distance metric learning is that the computational complexity for prediction (i. e. distance calculation) is relatively high especially when the dimension of input data becomes large. To calculate the distance effectively, we propose the way to derive low rank metric matrix with nuclear norm regularization. When solving the optimization problem, we use the alternating direction method of multiplier and proximal gradient. To verify the effectiveness of our proposed method from the viewpoint of classification accuracy and rank reduction, simulation experiments using benchmark data sets are conducted.

UR - http://www.scopus.com/inward/record.url?scp=85046154292&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046154292&partnerID=8YFLogxK

U2 - 10.1109/SSCI.2017.8280952

DO - 10.1109/SSCI.2017.8280952

M3 - Conference contribution

AN - SCOPUS:85046154292

VL - 2018-January

SP - 1

EP - 5

BT - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -