English

Classification with Costly Features as a Sequential Decision-Making Problem

Machine Learning 2020-03-05 v1 Artificial Intelligence Machine Learning

Abstract

This work focuses on a specific classification problem, where the information about a sample is not readily available, but has to be acquired for a cost, and there is a per-sample budget. Inspired by real-world use-cases, we analyze average and hard variations of a directly specified budget. We postulate the problem in its explicit formulation and then convert it into an equivalent MDP, that can be solved with deep reinforcement learning. Also, we evaluate a real-world inspired setting with sparse training dataset with missing features. The presented method performs robustly well in all settings across several distinct datasets, outperforming other prior-art algorithms. The method is flexible, as showcased with all mentioned modifications and can be improved with any domain independent advancement in RL.

Keywords

Cite

@article{arxiv.1909.02564,
  title  = {Classification with Costly Features as a Sequential Decision-Making Problem},
  author = {Jaromír Janisch and Tomáš Pevný and Viliam Lisý},
  journal= {arXiv preprint arXiv:1909.02564},
  year   = {2020}
}