Loading...
Loading...

Go to the content (press return)

Spectral learning of general weighted automata via constrained matrix completion

Author
B. Balle; Mohri, M.
Type of activity
Presentation of work at congresses
Name of edition
26th Annual Conference on Neural Information Processing Systems
Date of publication
2013
Presentation's date
2012-12-04
Book of congress proceedings
Advances in Neural Information Processing Systems 26: proceedings of the 2012 conference
First page
2168
Last page
2176
Rewarded activity
Yes
Project funding
Pattern Analysis, Statistical Modelling, and Computational Learning 2 (PASCAL2)
Repository
http://hdl.handle.net/2117/17754 Open in new window
URL
http://books.nips.cc/papers/files/nips25/bibhtml/NIPS2012_1075.html Open in new window
Abstract
Many tasks in text and speech processing and computational biology require estimating functions mapping strings to real numbers. A broad class of such functions can be defined by weighted automata. Spectral methods based on the singular value decomposition of a Hankel matrix have been recently proposed for learning a probability distribution represented by a weighted automaton from a training sample drawn according to this same target distribution. In this paper, we show how spectral methods can...
Citation
B. Balle; Mohri, M. Spectral learning of general weighted automata via constrained matrix completion. A: Annual Conference on Neural Information Processing Systems. "Advances in Neural Information Processing Systems 26: proceedings of the 2012 conference". Lake Tahoe, Nevada: 2012, p. 2168-2176.
Group of research
LARCA - Laboratory of Relational Algorithmics, Complexity and Learnability

Participants

  • De Balle Pigem, Borja  (author and speaker )
  • Mohri, Mehryar  (author and speaker )

Attachments