AISTATS 2023poster7 citations

Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models

Naoya Takeishi, Alexandros Kalousis

Abstract

The combination of deep neural nets and theory-driven models (deep grey-box models) can be advantageous due to the inherent robustness and interpretability of the theory-driven part. Deep grey-box models are usually learned with a regularized risk minimization to prevent a theory-driven part from being overwritten and ignored by a deep neural net. However, an estimation of the theory-driven part obtained by uncritically optimizing a regularizer can hardly be trustworthy if we are not sure which regularizer is suitable for the given data, which may affect the interpretability. Toward a trustworthy estimation of the theory-driven part, we should analyze the behavior of regularizers to compare different candidates and to justify a specific choice. In this paper, we present a framework that allows us to empirically analyze the behavior of a regularizer with a slight change in the architecture of the neural net and the training objective.

BibTeX
@InProceedings{pmlr-v206-takeishi23a,
  title = 	 {Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models},
  author =       {Takeishi, Naoya and Kalousis, Alexandros},
  booktitle = 	 {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {4089--4100},
  year = 	 {2023},
  editor = 	 {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem},
  volume = 	 {206},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {25--27 Apr},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v206/takeishi23a/takeishi23a.pdf},
  url = 	 {https://proceedings.mlr.press/v206/takeishi23a.html},
  abstract = 	 {The combination of deep neural nets and theory-driven models (deep grey-box models) can be advantageous due to the inherent robustness and interpretability of the theory-driven part. Deep grey-box models are usually learned with a regularized risk minimization to prevent a theory-driven part from being overwritten and ignored by a deep neural net. However, an estimation of the theory-driven part obtained by uncritically optimizing a regularizer can hardly be trustworthy if we are not sure which regularizer is suitable for the given data, which may affect the interpretability. Toward a trustworthy estimation of the theory-driven part, we should analyze the behavior of regularizers to compare different candidates and to justify a specific choice. In this paper, we present a framework that allows us to empirically analyze the behavior of a regularizer with a slight change in the architecture of the neural net and the training objective.}
}
Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models · AISTATS 2023