Branch & Learn for Recursively and Iteratively Solvable Problems in Predict+Optimize

Abstract

This paper proposes Branch & Learn, a framework for Predict+Optimize to tackle optimization problems containing parameters that are unknown at the time of solving. Given an optimization problem solvable by a recursive algorithm satisfying simple conditions, we show how a corresponding learning algorithm can be constructed directly and methodically from the recursive algorithm. Our framework applies also to iterative algorithms by viewing them as a degenerate form of recursion. Extensive experimentation shows better performance for our proposal over classical and state of the art approaches.

Cite

Text

Hu et al. "Branch & Learn for Recursively and Iteratively Solvable Problems in Predict+Optimize." Neural Information Processing Systems, 2022.

Markdown

[Hu et al. "Branch & Learn for Recursively and Iteratively Solvable Problems in Predict+Optimize." Neural Information Processing Systems, 2022.](https://mlanthology.org/neurips/2022/hu2022neurips-branch/)

BibTeX

@inproceedings{hu2022neurips-branch,
  title     = {{Branch & Learn for Recursively and Iteratively Solvable Problems in Predict+Optimize}},
  author    = {Hu, Xinyi and Lee, Jasper and Lee, Jimmy and Zhong, Allen Z.},
  booktitle = {Neural Information Processing Systems},
  year      = {2022},
  url       = {https://mlanthology.org/neurips/2022/hu2022neurips-branch/}
}