English

Learning Implicitly with Noisy Data in Linear Arithmetic

Artificial Intelligence 2021-09-08 v2 Logic in Computer Science

Abstract

Robust learning in expressive languages with real-world data continues to be a challenging task. Numerous conventional methods appeal to heuristics without any assurances of robustness. While probably approximately correct (PAC) Semantics offers strong guarantees, learning explicit representations is not tractable, even in propositional logic. However, recent work on so-called "implicit" learning has shown tremendous promise in terms of obtaining polynomial-time results for fragments of first-order logic. In this work, we extend implicit learning in PAC-Semantics to handle noisy data in the form of intervals and threshold uncertainty in the language of linear arithmetic. We prove that our extended framework keeps the existing polynomial-time complexity guarantees. Furthermore, we provide the first empirical investigation of this hitherto purely theoretical framework. Using benchmark problems, we show that our implicit approach to learning optimal linear programming objective constraints significantly outperforms an explicit approach in practice.

Keywords

Cite

@article{arxiv.2010.12619,
  title  = {Learning Implicitly with Noisy Data in Linear Arithmetic},
  author = {Alexander P. Rader and Ionela G. Mocanu and Vaishak Belle and Brendan Juba},
  journal= {arXiv preprint arXiv:2010.12619},
  year   = {2021}
}

Comments

This is an extended version of our IJCAI21 paper of the same name