### Abstract

Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation. Previous approaches for learning for structured prediction (e.g., cutting-plane, subgradient methods, perceptron) repeatedly make predictions for some of the data points. These approaches are computationally demanding because each prediction involves solving a linear program to optimally. We present a scalable algorithm for learning for structured prediction. The main idea is to instead solve the dual of the structured prediction loss. We formulate the learning task as a convex minimization over both the weights and the dual variables corresponding to each data point. As a result, we can begin to optimize the weights even before completely solving any of the individual prediction problems. We show how the dual variables can be efficiently optimized using co-ordinate descent. Our algorithm is competitive with state-of-the-art methods such as stochastic subgradient and cutting-plane.

Original language | English (US) |
---|---|

Title of host publication | ICML 2010 - Proceedings, 27th International Conference on Machine Learning |

Pages | 783-790 |

Number of pages | 8 |

State | Published - Sep 17 2010 |

Event | 27th International Conference on Machine Learning, ICML 2010 - Haifa, Israel Duration: Jun 21 2010 → Jun 25 2010 |

### Publication series

Name | ICML 2010 - Proceedings, 27th International Conference on Machine Learning |
---|

### Other

Other | 27th International Conference on Machine Learning, ICML 2010 |
---|---|

Country | Israel |

City | Haifa |

Period | 6/21/10 → 6/25/10 |

### Fingerprint

### ASJC Scopus subject areas

- Artificial Intelligence
- Education

### Cite this

*ICML 2010 - Proceedings, 27th International Conference on Machine Learning*(pp. 783-790). (ICML 2010 - Proceedings, 27th International Conference on Machine Learning).