ICML 2020poster8 citations

Partial Trace Regression and Low-Rank Kraus Decomposition

Hachem Kadri, Stephane Ayache, Riikka Huusari, Alain Rakotomamonjy, Ralaivola Liva

Abstract

The trace regression model, a direct extension of the well-studied linear regression model, allows one to map matrices to real-valued outputs. We here introduce an even more general model, namely the partial-trace regression model, a family of linear mappings from matrix-valued inputs to matrix-valued outputs; this model subsumes the trace regression model and thus the linear regression model. Borrowing tools from quantum information theory, where partial trace operators have been extensively studied, we propose a framework for learning partial trace regression models from data by taking advantage of the so-called low-rank Kraus representation of completely positive maps. We show the relevance of our framework with synthetic and real-world experiments conducted for both i) matrix-to-matrix regression and ii) positive semidefinite matrix completion, two tasks which can be formulated as partial trace regression problems.

BibTeX
@InProceedings{pmlr-v119-kadri20a,
  title = 	 {Partial Trace Regression and Low-Rank Kraus Decomposition},
  author =       {Kadri, Hachem and Ayache, Stephane and Huusari, Riikka and Rakotomamonjy, Alain and Liva, Ralaivola},
  booktitle = 	 {Proceedings of the 37th International Conference on Machine Learning},
  pages = 	 {5031--5041},
  year = 	 {2020},
  editor = 	 {III, Hal Daumé and Singh, Aarti},
  volume = 	 {119},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--18 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v119/kadri20a/kadri20a.pdf},
  url = 	 {https://proceedings.mlr.press/v119/kadri20a.html},
  abstract = 	 {The trace regression model, a direct extension of the well-studied linear regression model, allows one to map matrices to real-valued outputs. We here introduce an even more general model, namely the partial-trace regression model, a family of linear mappings from matrix-valued inputs to matrix-valued outputs; this model subsumes the trace regression model and thus the linear regression model. Borrowing tools from quantum information theory, where partial trace operators have been extensively studied, we propose a framework for learning partial trace regression models from data by taking advantage of the so-called low-rank Kraus representation of completely positive maps. We show the relevance of our framework with synthetic and real-world experiments conducted for both i) matrix-to-matrix regression and ii) positive semidefinite matrix completion, two tasks which can be formulated as partial trace regression problems.}
}
Partial Trace Regression and Low-Rank Kraus Decomposition · ICML 2020