Timezone: »
In structured output prediction tasks, labeling ground-truth training output is often expensive. However, for many tasks, even when the true output is unknown, we can evaluate predictions using a scalar reward function, which may be easily assembled from human knowledge or non-differentiable pipelines. But searching through the entire output space to find the best output with respect to this reward function is typically intractable. In this paper, we instead use efficient truncated randomized search in this reward function to train structured prediction energy networks (SPENs), which provide efficient test-time inference using gradient-based search on a smooth, learned representation of the score landscape, and have previously yielded state-of-the-art results in structured prediction. In particular, this truncated randomized search in the reward function yields previously unknown local improvements, providing effective supervision to SPENs, avoiding their traditional need for labeled training data.
Author Information
Pedram Rooshenas (University of Massachusetts Amherst)
Dongxu Zhang (University of Massachusetts Amherst)
Gopal Sharma (University of Massachusetts Amherst)
Andrew McCallum (UMass Amherst)
More from the Same Authors
-
2020 Poster: Improving Local Identifiability in Probabilistic Box Embeddings »
Shib Dasgupta · Michael Boratko · Dongxu Zhang · Luke Vilnis · Xiang Li · Andrew McCallum -
2019 Workshop: Sets and Partitions »
Nicholas Monath · Manzil Zaheer · Andrew McCallum · Ari Kobren · Junier Oliva · Barnabas Poczos · Ruslan Salakhutdinov -
2018 Poster: Compact Representation of Uncertainty in Clustering »
Craig Greenberg · Nicholas Monath · Ari Kobren · Patrick Flaherty · Andrew McGregor · Andrew McCallum -
2017 Poster: Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples »
Haw-Shiuan Chang · Erik Learned-Miller · Andrew McCallum -
2014 Workshop: 4th Workshop on Automated Knowledge Base Construction (AKBC) »
Sameer Singh · Fabian M Suchanek · Sebastian Riedel · Partha Pratim Talukdar · Kevin P Murphy · Christopher RĂ© · William Cohen · Tom Mitchell · Andrew McCallum · Jason E Weston · Ramanathan Guha · Boyan Onyshkevych · Hoifung Poon · Oren Etzioni · Ari Kobren · Arvind Neelakantan · Peter Clark -
2012 Poster: MAP Inference in Chains using Column Generation »
David Belanger · Alexandre T Passos · Sebastian Riedel · Andrew McCallum -
2011 Workshop: Big Learning: Algorithms, Systems, and Tools for Learning at Scale »
Joseph E Gonzalez · Sameer Singh · Graham Taylor · James Bergstra · Alice Zheng · Misha Bilenko · Yucheng Low · Yoshua Bengio · Michael Franklin · Carlos Guestrin · Andrew McCallum · Alexander Smola · Michael Jordan · Sugato Basu -
2011 Poster: Query-Aware MCMC »
Michael Wick · Andrew McCallum -
2009 Poster: FACTORIE: Probabilistic Programming via Imperatively Defined Factor Graphs »
Andrew McCallum · Karl Schultz · Sameer Singh -
2009 Poster: Training Factor Graphs with Reinforcement Learning for Efficient MAP Inference »
Michael Wick · Khashayar Rohanimanesh · Sameer Singh · Andrew McCallum -
2009 Spotlight: Training Factor Graphs with Reinforcement Learning for Efficient MAP Inference »
Michael Wick · Khashayar Rohanimanesh · Sameer Singh · Andrew McCallum -
2009 Poster: Rethinking LDA: Why Priors Matter »
Hanna Wallach · David Mimno · Andrew McCallum -
2009 Spotlight: Rethinking LDA: Why Priors Matter »
Hanna Wallach · David Mimno · Andrew McCallum