High-Dimensional Robust Mean Estimation via Gradient Descent
High-Dimensional Robust Mean Estimation via Gradient Descent
复制标题
DOI:
--
复制
发表时间:
2020-05
期刊:
影响因子:
--
通讯作者:
Yu Cheng;Ilias Diakonikolas;Rong Ge;M. Soltanolkotabi
中科院分区:
文献类型:
--
作者:
Yu Cheng;Ilias Diakonikolas;Rong Ge;M. Soltanolkotabi
We study the problem of high-dimensional robust mean estimation in the presence of a constant fraction of adversarial outliers. A recent line of work has provided sophisticated polynomial-time algorithms for this problem with dimension-independent error guarantees for a range of natural distribution families. In this work, we show that a natural non-convex formulation of the problem can be solved directly by gradient descent. Our approach leverages a novel structural lemma, roughly showing that any approximate stationary point of our non-convex objective gives a near-optimal solution to the underlying robust estimation task. Our work establishes an intriguing connection between algorithmic high-dimensional robust statistics and non-convex optimization, which may have broader applications to other robust estimation tasks.