On the Strategyproofness of the Geometric Median - Département de mathématiques appliquées Access content directly
Conference Papers Year : 2023

On the Strategyproofness of the Geometric Median

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 α-strategyproof : when the number of users is large enough, a user that misbehaves can gain at most a multiplicative factor α, 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 α. We also show how the skewed geometric medians can be used to improve strategyproofness.
Fichier principal
Vignette du fichier
el-mhamdi23a.pdf (1.08 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04363404 , version 1 (17-04-2024)

Identifiers

  • HAL Id : hal-04363404 , version 1

Cite

El-Mhamdi El-Mahdi, Farhadkhani Sadegh, Guerraoui Rachid, Hoang Lê-Nguyên. On the Strategyproofness of the Geometric Median. International Conference on Artificial Intelligence and Statistics, Apr 2023, Valencia, Spain. ⟨hal-04363404⟩
3 View
5 Download

Share

Gmail Facebook X LinkedIn More