## Find a copy online

### Links to this item

## Find a copy in the library

Finding libraries that hold this item...

## Details

Genre/Form: | text |
---|---|

Material Type: | Internet resource |

Document Type: | Internet Resource, Archival Material |

All Authors / Contributors: | Balle, Borja; Quattoni, Ariadna; Carreras, Xavier |

OCLC Number: | 815865081 |

### Abstract:

This paper re-visits the spectral method for learning latent variable models defined in terms of observable operators. We give a new perspective on the method, showing that operators can be recovered by minimizing a loss defined on a finite subset of the domain. A non-convex optimization similar to the spectral method is derived. We also propose a regularized convex relaxation of this optimization. We show that in practice the availabilty of a continuous regularization parameter (in contrast with the discrete number of states in the original method) allows a better trade-off between accuracy and model complexity. We also prove that in general, a randomized strategy for choosing the local loss will succeed with high probability.

Comment: Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

## Reviews

*User-contributed reviews*

Add a review and share your thoughts with other readers.
Be the first.

Add a review and share your thoughts with other readers.
Be the first.

## Tags

Add tags for "Local Loss Optimization in Operator Models: A New Insight into Spectral Learning".
Be the first.