Corpus ID: 211075853

Robust Mean Estimation under Coordinate-level Corruption

@article{Liu2020RobustME,
  title={Robust Mean Estimation under Coordinate-level Corruption},
  author={Zifan Liu and Jongho Park and Nils Palumbo and Theodoros Rekatsinas and Christos Tzamos},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.04137}
}
Data corruption, systematic or adversarial, may skew statistical estimation severely. Recent work provides computationally efficient estimators that nearly match the information-theoretic optimal statistic. Yet the corruption model they consider measures sample-level corruption and is not fine-grained enough for many real-world applications. In this paper, we propose a coordinate-level metric of distribution shift over high-dimensional settings with n coordinates. We introduce and analyze… Expand
2 Citations
Picket: Self-supervised Data Diagnostics for ML Pipelines
  • 1
  • PDF

References

SHOWING 1-10 OF 40 REFERENCES
Generalized Resilience and Robust Statistics
  • 15
  • PDF
Efficient Algorithms for Outlier-Robust Regression
  • 81
  • PDF
Robust Estimators in High Dimensions without the Computational Intractability
  • 209
  • PDF
Recent Advances in Algorithmic High-Dimensional Robust Statistics
  • 66
  • Highly Influential
  • PDF
Efficient Statistics, in High Dimensions, from Truncated Samples
  • 20
  • PDF
Agnostic Estimation of Mean and Covariance
  • 204
  • PDF
Efficient Truncated Statistics with Unknown Truncation
  • 8
  • PDF
...
1
2
3
4
...