ML Anthology

Sequential Learning Under Probabilistic Constraints

Amirhossein Meisami, Henry Lam, Chen Dong, Abhishek Pani
UAI 2018 pp. 621-631
/uai/2018/meisami2018uai-sequential/

Abstract

We provide the first study on online learning problems under stochastic constraints that are "soft", i.e., need to be satisfied with high probability. These constraints are imposed on all or some stages of the time horizon so that the stage decision probabilistically satisfies a safety condition that is realized after the decision is made. The distributions that govern these conditions are learned through the collected observations. Under a Bayesian framework, we study a scheme that provides statistical feasibility guarantees through the time horizon, by using posterior Monte Carlo samples to form sampled constraints that leverage the scenario generation approach in chance-constrained programming. We demonstrate how our scheme can be integrated into Thompson sampling and illustrate it with an application in online advertisement.

PDF UAI Semantic Scholar

Cite

Text

Meisami et al. "Sequential Learning Under Probabilistic Constraints." Conference on Uncertainty in Artificial Intelligence, 2018.

Markdown

[Meisami et al. "Sequential Learning Under Probabilistic Constraints." Conference on Uncertainty in Artificial Intelligence, 2018.](https://mlanthology.org/uai/2018/meisami2018uai-sequential/)

BibTeX

@inproceedings{meisami2018uai-sequential,
  title     = {{Sequential Learning Under Probabilistic Constraints}},
  author    = {Meisami, Amirhossein and Lam, Henry and Dong, Chen and Pani, Abhishek},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2018},
  pages     = {621-631},
  url       = {https://mlanthology.org/uai/2018/meisami2018uai-sequential/}
}