Recent Advances in Algorithmic High-Dimensional Robust Statistics
read the original abstract
Learning in the presence of outliers is a fundamental problem in statistics. Until recently, all known efficient unsupervised learning algorithms were very sensitive to outliers in high dimensions. In particular, even for the task of robust mean estimation under natural distributional assumptions, no efficient algorithm was known. Recent work in theoretical computer science gave the first efficient robust estimators for a number of fundamental statistical tasks, including mean and covariance estimation. Since then, there has been a flurry of research activity on algorithmic high-dimensional robust estimation in a range of settings. In this survey article, we introduce the core ideas and algorithmic techniques in the emerging area of algorithmic high-dimensional robust statistics with a focus on robust mean estimation. We also provide an overview of the approaches that have led to computationally efficient robust estimators for a range of broader statistical tasks and discuss new directions and opportunities for future work.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Disagreement-Regularized Importance Sampling for Adversarial Label Corruption
DR-IS selects low-contamination subsets via bounded rank-disagreement in proxy ensembles under an ε-contamination model, with O(√(log(N/δ)/K)) concentration rates that certify separation when the expectation gap Δ' is...
-
Mean Testing under Truncation beyond Gaussian
High-dimensional mean testing under truncation has an information-theoretic detectability floor from moment-based bias O(ν_{P,p} ε^{1-1/p}), with near-optimal second-order tests above it, and an escape to linear bias ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.