paper-with-me

Papers

On Robust Mean Estimation under Coordinate-level Corruption

2020-02-10 · Zifan Liu, Jongho Park, Theodoros Rekatsinas, Christos Tzamos

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.

📄 PDF Abstract BibTeX arXiv:2002.04137

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix Completion

Similar Papers 제목 키워드 기반

Robust Estimation Under Heterogeneous Corruption Rates

2025-08-20 · Syomantak Chaudhuri, Jerry Li, Thomas A. Courtade arxiv

We study the problem of robust estimation under heterogeneous corruption rates, where each sample may be independently corrupted with a known but non-identical probability. This setting arises naturally in distributed an…

Federated Learning

Linear Regression under Missing or Corrupted Coordinates

2025-09-23 · Ilias Diakonikolas, Jelena Diakonikolas, Daniel M. Kane, Jasper C. H. Lee 외 arxiv

We study multivariate linear regression under Gaussian covariates in two settings, where data may be erased or corrupted by an adversary under a coordinate-wise budget. In the incomplete data setting, an adversary may in…

SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations

2023-03-18 · ICCV 2023 1 · Boyan Wan, Yifei Shi, Kai Xu

Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling …

6D Pose Estimation6D Pose Estimation using RGBObjectPose Estimation+1

High-Dimensional Robust Mean Estimation with Untrusted Batches

2026-02-24 · Maryam Aliakbarpour, Vladimir Braverman, Yuhan Liu, Junze Yin arxiv

We study high-dimensional mean estimation in a collaborative setting where data is contributed by $N$ users in batches of size $n$. In this environment, a learner seeks to recover the mean $μ$ of a true distribution $P$ …

Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination

2024-03-15 · Ilias Diakonikolas, Daniel M. Kane, Sushrut Karmalkar, Ankit Pensia 외

We study Gaussian sparse estimation tasks in Huber's contamination model with a focus on mean estimation, PCA, and linear regression. For each of these tasks, we give the first sample and computationally efficient robust…