Learning Multiple Quantiles with Neural Networks

Sang Jun Moon, Jong‐June Jeon, J. S. H. Lee, Yongdai KimFigshare 2021 · DOI · OpenAlex

Abstract

We present a neural network model for estimation of multiple conditional quantiles that satisfies the non-crossing property. Motivated by linear non-crossing quantile regression, we propose a non-crossing quantile neural network model with inequality constraints. In particular, to use the first-order optimization method, we develop a new algorithm for fitting the proposed model. This algorithm gives a nearly optimal solution without the projected gradient step that requires polynomial computation time. We compare the performance of our proposed model with that of existing neural network models on simulated and real precipitation data.
BibTeX
@inproceedings{moon2021learning,
  author = {Sang Jun Moon and Jong‐June Jeon and J. S. H. Lee and Yongdai Kim},
  title = {{Learning Multiple Quantiles with Neural Networks}},
  booktitle = {Figshare},
  year = {2021},
  doi = {10.6084/m9.figshare.14336625.v1},
}

Loading related content...

Figure