Geometric Median Matching for Robust k-Subset Selection from Noisy Data

Anish Acharya; S Sanghavi; A G Dimakis; I S Dhillon

Geometric Median Matching for Robust k-Subset Selection from Noisy Data

Anish Acharya, S Sanghavi, A G Dimakis, I S Dhillon

International Conference on Machine Learning (ICML), 2025

Selects a k-subset whose mean tracks the geometric median of noisy data, giving an O(1/k) rate under arbitrary corruption, a quadratic improvement over random sampling.

PMLR OpenReview arXiv

Short version: ICML 2024 FMWild Workshop

All publications · Research