ML Anthology

Some Properties of Batch Value of Information in the Selection Problem (Extended Abstract)

Shahaf S. Shperberg, Solomon Eyal Shimony
IJCAI 2017 pp. 5065-5069
doi:10.24963/IJCAI.2017/723 /ijcai/2017/shperberg2017ijcai-some/

Abstract

We examine theoretical properties of value of information (VOI) in the selection problem, and identify cases of submodularity and supermodularity. We use these properties to compute approximately optimal measurement batch policies, implemented on a “wine selection problem” example.

PDF IJCAI Semantic Scholar

Cite

Text

Shperberg and Shimony. "Some Properties of Batch Value of Information in the Selection Problem (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/723

Markdown

[Shperberg and Shimony. "Some Properties of Batch Value of Information in the Selection Problem (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/shperberg2017ijcai-some/) doi:10.24963/IJCAI.2017/723

BibTeX

@inproceedings{shperberg2017ijcai-some,
  title     = {{Some Properties of Batch Value of Information in the Selection Problem (Extended Abstract)}},
  author    = {Shperberg, Shahaf S. and Shimony, Solomon Eyal},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {5065-5069},
  doi       = {10.24963/IJCAI.2017/723},
  url       = {https://mlanthology.org/ijcai/2017/shperberg2017ijcai-some/}
}