When does the Tukey median work?
Not on the map. Why?
Abstract (arXiv)
We analyze the performance of the Tukey median estimator under total variation (TV) distance corruptions. Previous results show that under Huber's additive corruption model, the breakdown point is 1/3 for high-dimensional halfspace-symmetric distributions. We show that under TV corruptions, the breakdown point reduces to 1/4 for the same set of distributions. We also show that a certain projection algorithm can attain the optimal breakdown point of 1/2. Both the Tukey median estimator and the projection algorithm achieve sample complexity linear in dimension.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jan 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 3; 2023: 1.
5 papers.
- 2021Robust and Differentially Private Mean Estimationcited by 66
- 2022Sentence-level Privacy for Document Embeddingscited by 15
- 2022Robust Estimation for Nonparametric Families via Generative Adversarial Networkscited by 3
- 2022Differentially private multivariate medianscited by 2
- 2023Noisy Computing of the mathsfOR and mathsfMAX Functionscited by 1
- 2023Noisy Computing of the mathsfOR and mathsfMAX Functions7 Sep 2023
- 2022Differentially private multivariate medians12 Oct 2022
- 2022Sentence-level Privacy for Document Embeddings10 May 2022
- 2022Robust Estimation for Nonparametric Families via Generative Adversarial Networks2 Feb 2022
- 2021Robust and Differentially Private Mean Estimation18 Feb 2021