End-to-End Learning for Structured Prediction Energy Networks

Abstract

Structured Prediction Energy Networks (SPENs) are a simple, yet expressive family of structured prediction models (Belanger and McCallum, 2016). An energy function over candidate structured outputs is given by a deep network, and predictions are formed by gradient-based optimization. This paper presents end-to-end learning for SPENs, where the energy function is discriminatively trained by back-propagating through gradient-based prediction. In our experience, the approach is substantially more accurate than the structured SVM method of Belanger and McCallum (2016), as it allows us to use more sophisticated non-convex energies. We provide a collection of techniques for improving the speed, accuracy, and memory requirements of end-to-end SPENs, and demonstrate the power of our method on 7-Scenes image denoising and CoNLL-2005 semantic role labeling tasks. In both, inexact minimization of non-convex SPEN energies is superior to baseline methods that use simplistic energy functions that can be minimized exactly.

ICML 2017

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• Gradient-based Hyperparameter Optimization through Reversible Learning
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Block-Coordinate Frank-Wolfe Optimization for Structural SVMs
• Highway and Residual Networks learn Unrolled Iterative Estimation

Cited by in corpus (11)

• OptNet: Differentiable Optimization as a Layer in Neural Networks
• SparseMAP: Differentiable Sparse Structured Inference
• End-to-End Learning for the Deep Multivariate Probit Model
• Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization
• An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search
• End-to-end learning potentials for structured attribute prediction
• Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
• Learning Discriminators as Energy Networks in Adversarial Learning
• Deep Structured Reactive Planning
• Proximal Mapping for Deep Regularization
• Structured Prediction in NLP -- A survey