More data means less inference: A pseudo-max approach to structured learning
Author(s)Sontag, David; Meshi, Ofer; Jaakkola, Tommi S.; Globerson, Amir
MetadataShow full item record
The problem of learning to predict structured labels is of key importance in many applications. However, for general graph structure both learning and inference in this setting are intractable. Here we show that it is possible to circumvent this difficulty when the input distribution is rich enough via a method similar in spirit to pseudo-likelihood. We show how our new method achieves consistency, and illustrate empirically that it indeed performs as well as exact methods when sufficiently large training sets are used.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Poster Session paper of the Twenty-Fourth Annual Conference on Neural Information Processing Systems, NIPS 2010
Neural Information Processing Systems Foundation
Sontag, David et al. "More data means less inference: A pseudo-max approach to structured learning." in Proceedins of the Twenty-Fourth Annual Conference on Neural Information Processing Systems, NIPS 2010, Poster Session, December 6-9, Vancouver, B.C., Canada.
Author's final manuscript