AIConfPaper
ICML 2022spotlight15 citations

On Learning Mixture of Linear Regressions in the Non-Realizable Setting

Soumyabrata Pal, Arya Mazumdar, Rajat Sen, Avishek Ghosh

Source ↗PDF ↗Scholar ↗

Abstract

While mixture of linear regressions (MLR) is a well-studied topic, prior works usually do not analyze such models for prediction error. In fact,

BibTeX
@InProceedings{pmlr-v162-pal22b,
  title = 	 {On Learning Mixture of Linear Regressions in the Non-Realizable Setting},
  author =       {Pal, Soumyabrata and Mazumdar, Arya and Sen, Rajat and Ghosh, Avishek},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {17202--17220},
  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/pal22b/pal22b.pdf},
  url = 	 {https://proceedings.mlr.press/v162/pal22b.html},
  abstract = 	 {While mixture of linear regressions (MLR) is a well-studied topic, prior works usually do not analyze such models for prediction error. In fact,
On Learning Mixture of Linear Regressions in the Non-Realizable Setting · ICML 2022