Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.
Author ORCID Identifier
N/A
AccessType
Open Access Dissertation
Document Type
dissertation
Degree Name
Doctor of Philosophy (PhD)
Degree Program
Computer Science
Year Degree Awarded
2017
Month Degree Awarded
September
First Advisor
Andrew McCallum
Subject Categories
Applied Statistics | Artificial Intelligence and Robotics
Abstract
We introduce structured prediction energy networks (SPENs), a flexible frame- work for structured prediction. A deep architecture is used to define an energy func- tion over candidate outputs and predictions are produced by gradient-based energy minimization. This deep energy captures dependencies between labels that would lead to intractable graphical models, and allows us to automatically discover discrim- inative features of the structured output. Furthermore, practitioners can explore a wide variety of energy function architectures without having to hand-design predic- tion and learning methods for each model. This is because all of our prediction and learning methods interact with the energy only via the standard interface for deep networks: forward and back-propagation. In a variety of applications, we find that we can obtain better accuracy using approximate minimization of non-convex deep energy functions than baseline models that employ simple energy functions for which exact minimization is tractable.
DOI
https://doi.org/10.7275/10699508.0
Recommended Citation
Belanger, David, "Deep Energy-Based Models for Structured Prediction" (2017). Doctoral Dissertations. 1030.
https://doi.org/10.7275/10699508.0
https://scholarworks.umass.edu/dissertations_2/1030