On Robust Mean Estimation under Coordinate-level Corruption
arXiv:2002.04137
Abstract
We study the problem of robust mean estimation and introduce a novel Hamming distance-based measure of distribution shift for coordinate-level corruptions. We show that this measure yields adversary models that capture more realistic corruptions than those used in prior works, and present an information-theoretic analysis of robust mean estimation in these settings. We show that for structured distributions, methods that leverage the structure yield information theoretically more accurate mean estimation. We also focus on practical algorithms for robust mean estimation and study when data cleaning-inspired approaches that first fix corruptions in the input data and then perform robust mean estimation can match the information theoretic bounds of our analysis. We finally demonstrate experimentally that this two-step approach outperforms structure-agnostic robust estimation and provides accurate mean estimation even for high-magnitude corruption.
arXiv comment21 pages, 5 figures
References in corpus (6)
- Recent Advances in Algorithmic High-Dimensional Robust Statistics
- A Characterization of Deterministic Sampling Patterns for Low-Rank Matrix Completion
- Phocas: dimensional Byzantine-resilient stochastic gradient descent
- Generalized Resilience and Robust Statistics
- Faster Algorithms for High-Dimensional Robust Covariance Estimation
- Robust Subspace Recovery with Adversarial Outliers