Proceedings

Fine-grained Generalization Analysis of Structured Output Prediction

Waleed Mustafa, Yunwen Lei, Antoine Ledent, Marius Kloft

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 2841-2847.

https://doi.org/10.24963/ijcai.2021/391

Keywords

  • Machine Learning: Learning Theory
  • Machine Learning: Structured Prediction

Abstract

In machine learning we often encounter structured output prediction problems (SOPPs), i.e. problems where the output space admits a rich internal structure. Application domains where SOPPs naturally occur include natural language processing, speech recognition, and computer vision. Typical SOPPs have an extremely large label set, which grows exponentially as a function of the size of the output. Existing generalization analysis implies generalization bounds with at least a square-root dependency on the cardinality d of the label set, which can be vacuous in practice. In this paper, we significantly improve the state of the art by developing novel high-probability bounds with a logarithmic dependency on d. Furthermore, we leverage the lens of algorithmic stability to develop generalization bounds in expectation without any dependency on d. Our results therefore build a solid theoretical foundation for learning in large-scale SOPPs. Furthermore, we extend our results to learning with weakly dependent data.

Waleed Mustafa, Yunwen Lei, Antoine Ledent, and Marius Kloft. 2021. Fine-grained Generalization Analysis of Structured Output Prediction. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 2841–2847. https://doi.org/10.24963/ijcai.2021/391
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards