Ankit Pensia

Featured in:

Articles

Optimal Robust Estimation under Local and Global Corruptions: Stronger Adversary and Smaller Error

Oct 22, 2024 | arxiv.org | Ankit Pensia

Open access is only possible with YOUR support. Give to arXiv this week to help keep science open for all.
[2403.10416] Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination

Mar 15, 2024 | arxiv.org | Daniel Kane |Sushrut Karmalkar |Ankit Pensia |Thanasis Pittas
[2305.02544] Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA

May 4, 2023 | arxiv.org | Daniel Kane |Ankit Pensia |Thanasis Pittas

We study principal component analysis (PCA), where given a dataset in $\mathbb{R}^d$ from a distribution, the task is to find a unit vector $v$ that approximately maximizes the variance of the distribution after being projected along $v$. Despite being a classical task, standard estimators fail drastically if the data contains even a small fraction of outliers, motivating the problem of robust PCA.
[2204.12399] Streaming Algorithms for High-Dimensional Robust Statistics

May 3, 2023 | arxiv.org | Daniel Kane |Ankit Pensia |Thanasis Pittas

[Submitted on 26 Apr 2022 (v1), last revised 3 May 2023 (this version, v2)] Title:Streaming Algorithms for High-Dimensional Robust Statistics Download a PDF of the paper titled Streaming Algorithms for High-Dimensional Robust Statistics, by Ilias Diakonikolas and 3 other authors Download PDF Abstract: We study high-dimensional robust statistics tasks in the streaming model.