Skip to yearly menu bar Skip to main content


On the Strategyproofness of the Geometric Median

El-Mahdi El-Mhamdi · Sadegh Farhadkhani · Rachid Guerraoui · Lê-Nguyên Hoang

Auditorium 1 Foyer 91

Abstract: The geometric median, an instrumental component of the secure machine learning toolbox, is known to be effective when robustly aggregating models (or gradients), gathered from potentially malicious (or strategic) users. What is less known is the extent to which the geometric median incentivizes dishonest behaviors. This paper addresses this fundamental question by quantifying its strategyproofness. While we observe that the geometric median is not even approximately strategyproof, we prove that it is asymptotically $\alpha$-strategyproof: when the number of users is large enough, a user that misbehaves can gain at most a multiplicative factor $\alpha$, which we compute as a function of the distribution followed by the users. We then generalize our results to the case where users actually care more about specific dimensions, determining how this impacts $\alpha$. We also show how the skewed geometric medians can be used to improve strategyproofness.

Live content is unavailable. Log in and register to view live content