The Broader Landscape of Robustness in Algorithmic Statistics
Not on the map. Why?
Abstract (arXiv)
The last decade has seen a number of advances in computationally efficient algorithms for statistical methods subject to robustness constraints. An estimator may be robust in a number of different ways: to contamination of the dataset, to heavy-tailed data, or in the sense that it preserves privacy of the dataset. We survey recent results in these areas with a focus on the problem of mean estimation, drawing technical and conceptual connections between the various forms of robustness, showing that the same underlying algorithmic ideas lead to computationally efficient estimators in all these settings.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 39 of its 63 references that are in the map. First posted on arXiv 3 Dec 2024.
Builds on
39 of 63 references.
References · 39
- 2017Certified Defenses for Data Poisoning Attackscited by 288
- 2016Robust Estimators in High Dimensions without the Computational Intractabilitycited by 209
- 2016Agnostic Estimation of Mean and Covariancecited by 131
- 2018Sever: A Robust Meta-Algorithm for Stochastic Optimizationcited by 123
- 2016Statistical Query Lower Bounds for Robust Estimation of High-dimensional Gaussians and Gaussian Mixturescited by 114
- 2017Finite Sample Differentially Private Confidence Intervalscited by 103
- 2018Privately Learning High-Dimensional Distributionscited by 103
- 2019Recent Advances in Algorithmic High-Dimensional Robust Statisticscited by 100
- 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
- 2017Being Robust (in High Dimensions) Can Be Practicalcited by 83
- 2020Private Mean Estimation of Heavy-Tailed Distributionscited by 73
- 2021Robust and Differentially Private Mean Estimationcited by 66
27 more
- 2021Differential privacy and robust statistics in high dimensionscited by 64
- 2019Private Hypothesis Selectioncited by 60
- 2020Outlier Robust Mean Estimation with Subgaussian Rates via Stabilitycited by 50
- 2021Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanismcited by 50
- 2015Robust Covariance and Scatter Matrix Estimation under Huber's Contamination Modelcited by 47
- 2017Sub-Gaussian estimators of the mean of a random vectorcited by 47
- 2022Robustness Implies Privacy in Statistical Estimationcited by 47
- 2021Covariance-Aware Private Mean Estimation Without Private Covariance Estimationcited by 46
- 2020Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimizationcited by 44
- 2017Resilience: A Criterion for Learning in the Presence of Arbitrary Outlierscited by 43
- 2017Robustly Learning a Gaussian: Getting Optimal Error, Efficientlycited by 39
- 2021Private and polynomial time algorithms for learning Gaussians and beyondcited by 39
- 2016Geometric Median in Nearly Linear Timecited by 38
- 2021Private Robust Estimation by Stabilizing Convex Relaxationscited by 38
- 2019Robust subgaussian estimation of a mean vector in nearly linear timecited by 37
- 2019Generalized Resilience and Robust Statisticscited by 37
- 2018Mean Estimation with Sub-Gaussian Rates in Polynomial Timecited by 33
- 2023From Robustness to Privacy and Backcited by 27
- 2018High-dimensional estimation via sum-of-squares proofscited by 25
- 2022Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimationcited by 25
- 2023Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributionscited by 22
- 2019Fast Mean Estimation with Sub-Gaussian Ratescited by 18
- 2021On the power of adaptivity in statistical adversariescited by 12
- 2024Adaptive and oblivious statistical adversaries are equivalentcited by 9
- 2022Robust estimation algorithms don't need to know the corruption levelcited by 4
- 2024Distribution Learnability and Robustnesscited by 4
- 2024Outlier-robust Mean Estimation near the Breakdown Point via Sum-of-Squarescited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.