# SEARNN: Training RNNs with Global-Local Losses

arXiv: https://arxiv.org/abs/1706.04499 · HTML: https://mlsanity.com/paper/1706.04499/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2017.

## Built on by (most cited first, 17 of 17)

- [Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization](https://mlsanity.com/paper/2210.01241/) (2022)
- [ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis](https://mlsanity.com/paper/2108.08827/) (2021)
- [Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation](https://mlsanity.com/paper/2204.01171/) (2022)
- [Autoregressive Knowledge Distillation through Imitation Learning](https://mlsanity.com/paper/2009.07253/) (2020)
- [Text Generation by Learning from Demonstrations](https://mlsanity.com/paper/2009.07839/) (2020)
- [Machine Translation Decoding beyond Beam Search](https://mlsanity.com/paper/2104.05336/) (2021)
- [Learning to Generate Better Than Your LLM](https://mlsanity.com/paper/2306.11816/) (2023)
- [An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models](https://mlsanity.com/paper/2203.09486/) (2022)
- [Active Imitation Learning with Noisy Guidance](https://mlsanity.com/paper/2005.12801/) (2020)
- [Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play](https://mlsanity.com/paper/2210.12096/) (2022)
- [Mixed Cross Entropy Loss for Neural Machine Translation](https://mlsanity.com/paper/2106.15880/) (2021)
- [Defining error accumulation in ML atmospheric simulators](https://mlsanity.com/paper/2405.14714/) (2024)
- [DiffusionRollout: Uncertainty-Aware Rollout Planning in Long-Horizon PDE Solving](https://mlsanity.com/paper/2602.13616/) (2026)
- [Structured Convolutional Kernel Networks for Airline Crew Scheduling](https://mlsanity.com/paper/2105.11646/) (2021)
- [Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation](https://mlsanity.com/paper/2109.06308/) (2021)
- [Regularization of ML models for Earth systems by using longer model timesteps](https://mlsanity.com/paper/2503.18023/) (2025)
- [Alleviate Exposure Bias in Sequence Prediction  with Recurrent Neural Networks](https://mlsanity.com/paper/2103.11603/) (2021)

## Abstract (arXiv)

We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the "learning to search" (L2S) approach to structured prediction. RNNs have been widely successful in structured prediction applications such as machine translation or parsing, and are commonly trained using maximum likelihood estimation (MLE). Unfortunately, this training loss is not always an appropriate surrogate for the test error: by only maximizing the ground truth probability, it fails to exploit the wealth of information offered by structured losses. Further, it introduces discrepancies between training and predicting (such as exposure bias) that may hurt test performance. Instead, SEARNN leverages test-alike search space exploration to introduce global-local losses that are closer to the test error. We first demonstrate improved performance over MLE on two different tasks: OCR and spelling correction. Then, we propose a subsampling strategy to enable SEARNN to scale to large vocabulary sizes. This allows us to validate the benefits of our approach on a machine translation task.