Distributed estimation of the inverse Hessian by determinantal averaging

Michal Derezinski; Michael W. Mahoney

NeurIPS 2019poster37 citations

Distributed estimation of the inverse Hessian by determinantal averaging

Abstract

In distributed optimization and distributed numerical linear algebra, we often encounter an inversion bias: if we want to compute a quantity that depends on the inverse of a sum of distributed matrices, then the sum of the inverses does not equal the inverse of the sum.

BibTeX

@inproceedings{NEURIPS2019_b1b20d09,
 author = {Derezinski, Michal and Mahoney, Michael W},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Distributed estimation of the inverse Hessian by determinantal averaging},
 url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/b1b20d09041289e6c3fbb81850c5da54-Paper.pdf},
 volume = {32},
 year = {2019}
}