Robustly learning mixtures of k arbitrary Gaussians
Robustly learning mixtures of k arbitrary Gaussians
复制标题
鲁棒地学习 k 个任意高斯的混合
DOI:
10.1145/3519935.3519953
复制
发表时间:
2022
期刊:
影响因子:
--
通讯作者:
Vempala, Santosh S.
中科院分区:
文献类型:
--
作者:
Bakshi, Ainesh;Diakonikolas, Ilias;Jia, He;Kane, Daniel M.;Kothari, Pravesh K.;Vempala, Santosh S.
We give a polynomial-time algorithm for the problem of robustly estimating a mixture ofkarbitrary Gaussians in ℝd, for any fixedk, in the presence of a constant fraction of arbitrary corruptions. This resolves the main open problem in several previous works on algorithmic robust statistics, which addressed the special cases of robustly estimating (a) a single Gaussian, (b) a mixture of TV-distance separated Gaussians, and (c) a uniform mixture of two Gaussians. Our main tools are an efficientpartial clusteringalgorithm that relies on the sum-of-squares method, and a noveltensor decompositionalgorithm that allows errors in both Frobenius norm and low-rank terms.
登录
查看更多内容
DOI:
--
发表时间:
2019
期刊:
Advances in neural information processing systems
影响因子:
--
作者:
Karmalkar, Sushrut;Klivans, Adam;Kothari, Pravesh
通讯作者:
Kothari, Pravesh
DOI:
--
发表时间:
2017
期刊:
arXiv.org
影响因子:
--
作者:
Pravesh Kothari;David Steurer
通讯作者:
David Steurer
DOI:
--
发表时间:
2020
期刊:
arXiv.org
影响因子:
--
作者:
Ainesh Bakshi;Pravesh Kothari
通讯作者:
Pravesh Kothari
DOI:
10.1145/3188745.3188758
发表时间:
2017-11
期刊:
Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing
影响因子:
--
作者:
Ilias Diakonikolas;D. Kane;Alistair Stewart
通讯作者:
Ilias Diakonikolas;D. Kane;Alistair Stewart
DOI:
10.1016/s0169-7161(97)15005-2
发表时间:
1996
期刊:
Handbook of Statistics
影响因子:
--
作者:
M. Markatou;E. Ronchetti
通讯作者:
E. Ronchetti