English

From Predictions to Decisions: The Importance of Joint Predictive Distributions

Machine Learning 2022-05-25 v3 Machine Learning

Abstract

A fundamental challenge for any intelligent system is prediction: given some inputs, can you predict corresponding outcomes? Most work on supervised learning has focused on producing accurate marginal predictions for each input. However, we show that for a broad class of decision problems, accurate joint predictions are required to deliver good performance. In particular, we establish several results pertaining to combinatorial decision problems, sequential predictions, and multi-armed bandits to elucidate the essential role of joint predictive distributions. Our treatment of multi-armed bandits introduces an approximate Thompson sampling algorithm and analytic techniques that lead to a new kind of regret bound.

Keywords

Cite

@article{arxiv.2107.09224,
  title  = {From Predictions to Decisions: The Importance of Joint Predictive Distributions},
  author = {Zheng Wen and Ian Osband and Chao Qin and Xiuyuan Lu and Morteza Ibrahimi and Vikranth Dwaracherla and Mohammad Asghari and Benjamin Van Roy},
  journal= {arXiv preprint arXiv:2107.09224},
  year   = {2022}
}