2000 character limit reached
When does the Tukey median work? (2001.07805v2)
Published 21 Jan 2020 in math.ST, cs.LG, eess.SP, stat.ML, and stat.TH
Abstract: 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.