ICML 2022spotlight5 citations

Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time

Burak Bartan, Mert Pilanci

Abstract

Fisher’s Linear Discriminant Analysis (FLDA) is a statistical analysis method that linearly embeds data points to a lower dimensional space to maximize a discrimination criterion such that the variance between classes is maximized while the variance within classes is minimized. We introduce a natural extension of FLDA that employs neural networks, called Neural Fisher Discriminant Analysis (NFDA). This method finds the optimal two-layer neural network that embeds data points to optimize the same discrimination criterion. We use tools from convex optimization to transform the optimal neural network embedding problem into a convex problem. The resulting problem is easy to interpret and solve to global optimality. We evaluate the method’s performance on synthetic and real datasets.

BibTeX
@InProceedings{pmlr-v162-bartan22a,
  title = 	 {Neural {F}isher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time},
  author =       {Bartan, Burak and Pilanci, Mert},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {1647--1663},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/bartan22a/bartan22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/bartan22a.html},
  abstract = 	 {Fisher’s Linear Discriminant Analysis (FLDA) is a statistical analysis method that linearly embeds data points to a lower dimensional space to maximize a discrimination criterion such that the variance between classes is maximized while the variance within classes is minimized. We introduce a natural extension of FLDA that employs neural networks, called Neural Fisher Discriminant Analysis (NFDA). This method finds the optimal two-layer neural network that embeds data points to optimize the same discrimination criterion. We use tools from convex optimization to transform the optimal neural network embedding problem into a convex problem. The resulting problem is easy to interpret and solve to global optimality. We evaluate the method’s performance on synthetic and real datasets.}
}
Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time · ICML 2022