9 citations · 40 across the 11 of their papers we have counts for
11 papers
Solidago: A Modular Collaborative Scoring Pipeline
Lê Nguyên Hoang, Romain Beylerian, Bérangère Colbois +6
This paper presents Solidago, an end-to-end modular pipeline to allow any community of users to collaboratively score any number of entities. Solidago proposes a six-module decompo…
On the Impossible Safety of Large AI Models
El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui +5
Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance. However they have been empirically found to pos…
Robust Collaborative Learning with Linear Gradient Overhead
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta +3
Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware…
Robust Sparse Voting
Youssef Allouah, Rachid Guerraoui, Lê-Nguyên Hoang +1
Many applications, such as content moderation and recommendation, require reviewing and scoring a large number of alternatives. Doing so robustly is however very challenging. Indee…
An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Sadegh Farhadkhani, Rachid Guerraoui, Lê-Nguyên Hoang +1
To study the resilience of distributed learning, the "Byzantine" literature considers a strong threat model where workers can report arbitrary gradients to the parameter server. Wh…
Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments
Lê-Nguyên Hoang, Louis Faucon, Aidan Jungo +13
Today's large-scale algorithms have become immensely influential, as they recommend and moderate the content that billions of humans are exposed to on a daily basis. They are the d…
Strategyproof Learning: Building Trustworthy User-Generated Datasets
Sadegh Farhadkhani, Rachid Guerraoui, Lê-Nguyên Hoang
We prove in this paper that, perhaps surprisingly, incentivizing data misreporting is not a fatality. By leveraging a careful design of the loss function, we propose Licchavi, a gl…
On the Strategyproofness of the Geometric Median
El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui +1
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 pote…
Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)
El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui +3
We study Byzantine collaborative learning, where nodes seek to collectively learn from each others' local data. The data distribution may vary from one node to another. No node…
A Roadmap for Robust End-to-End Alignment
Lê Nguyên Hoang
This paper discussed the {\it robust alignment} problem, that is, the problem of aligning the goals of algorithms with human preferences. It presented a general roadmap to tackle t…
Deep Learning Works in Practice. But Does it Work in Theory?
Lê Nguyên Hoang, Rachid Guerraoui
Deep learning relies on a very specific kind of neural networks: those superposing several neural layers. In the last few years, deep learning achieved major breakthroughs in many…