# Implicit Training of Energy Model for Structure Prediction

arXiv: https://arxiv.org/abs/2211.11649 · HTML: https://mlsanity.com/paper/2211.11649/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 82 references that are in the map.
- First posted on arXiv 21 Nov 2022.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [OptNet: Differentiable Optimization as a Layer in Neural Networks](https://mlsanity.com/paper/1703.00443/) (2017)
- [Meta-Learning with Implicit Gradients](https://mlsanity.com/paper/1909.04630/) (2019)
- [Differentiable Convex Optimization Layers](https://mlsanity.com/paper/1910.12430/) (2019)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Bilevel Programming for Hyperparameter Optimization and Meta-Learning](https://mlsanity.com/paper/1806.04910/) (2018)
- [Gradient-based Hyperparameter Optimization through Reversible Learning](https://mlsanity.com/paper/1502.03492/) (2015)
- [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://mlsanity.com/paper/1911.02590/) (2019)
- [Forward and Reverse Gradient-Based Hyperparameter Optimization](https://mlsanity.com/paper/1703.01785/) (2017)
- [Differentiation of Blackbox Combinatorial Solvers](https://mlsanity.com/paper/1912.02175/) (2019)
- [Learning to Optimize](https://mlsanity.com/paper/1606.01885/) (2016)
- [Meta-Reinforcement Learning of Structured Exploration Strategies](https://mlsanity.com/paper/1802.07245/) (2018)
- [Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency](https://mlsanity.com/paper/1809.01812/) (2018)
- [On Learning Intrinsic Rewards for Policy Gradient Methods](https://mlsanity.com/paper/1804.06459/) (2018)
- [Residual Energy-Based Models for Text Generation](https://mlsanity.com/paper/2004.11714/) (2020)
- [SGM: Sequence Generation Model for Multi-label Classification](https://mlsanity.com/paper/1806.04822/) (2018)
- [Evolved Policy Gradients](https://mlsanity.com/paper/1802.04821/) (2018)
- [Discovering Reinforcement Learning Algorithms](https://mlsanity.com/paper/2007.08794/) (2020)
- [Meta-Learning via Learned Loss](https://mlsanity.com/paper/1906.05374/) (2019)
- [Structured Prediction Energy Networks](https://mlsanity.com/paper/1511.06350/) (2015)
- [Classical Structured Prediction Losses for Sequence to Sequence Learning](https://mlsanity.com/paper/1711.04956/) (2017)
- [Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models](https://mlsanity.com/paper/2009.13267/) (2020)
- [Learning to Teach with Dynamic Loss Functions](https://mlsanity.com/paper/1810.12081/) (2018)
- [Structured Output Learning with Conditional Generative Flows](https://mlsanity.com/paper/1905.13288/) (2019)
- [ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2005.00850/) (2020)
- [End-to-End Learning for Structured Prediction Energy Networks](https://mlsanity.com/paper/1703.05667/) (2017)

## Abstract (arXiv)

Most deep learning research has focused on developing new model and training procedures. On the other hand the training objective has usually been restricted to combinations of standard losses. When the objective aligns well with the evaluation metric, this is not a major issue. However when dealing with complex structured outputs, the ideal objective can be hard to optimize and the efficacy of usual objectives as a proxy for the true objective can be questionable. In this work, we argue that the existing inference network based structure prediction methods ( Tu and Gimpel 2018; Tu, Pang, and Gimpel 2020) are indirectly learning to optimize a dynamic loss objective parameterized by the energy model. We then explore using implicit-gradient based technique to learn the corresponding dynamic objectives. Our experiments show that implicitly learning a dynamic loss landscape is an effective method for improving model performance in structure prediction.