Search Results for author: El Mahdi El Mhamdi

Found 14 papers, 5 papers with code

Incentivized Learning in Principal-Agent Bandit Games

no code implementations6 Mar 2024 Antoine Scheid, Daniil Tiapkin, Etienne Boursier, Aymeric Capitaine, El Mahdi El Mhamdi, Eric Moulines, Michael I. Jordan, Alain Durmus

This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent.

Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent

no code implementations ICLR 2021 El Mahdi El Mhamdi, Rachid Guerraoui, Sébastien Rouault

We propose a practical method which, despite increasing the variance, reduces the variance-norm ratio, mitigating the identified weakness.

Host-Pathongen Co-evolution Inspired Algorithm Enables Robust GAN Training

1 code implementation22 May 2020 Andrei Kucharavy, El Mahdi El Mhamdi, Rachid Guerraoui

Generative adversarial networks (GANs) are pairs of artificial neural networks that are trained one against each other.

Fast Machine Learning with Byzantine Workers and Servers

no code implementations18 Nov 2019 El Mahdi El Mhamdi, Rachid Guerraoui, Arsany Guirguis

We moreover show that the throughput gain of LiuBei compared to another state-of-the-art Byzantine-resilient ML algorithm (that assumes network asynchrony) is 70%.

BIG-bench Machine Learning

Removing Algorithmic Discrimination (With Minimal Individual Error)

no code implementations7 Jun 2018 El Mahdi El Mhamdi, Rachid Guerraoui, Lê Nguyên Hoang, Alexandre Maurer

We first solve the problem analytically in the case of two populations, with a uniform bonus-malus on the zones where each population is a majority.

Virtuously Safe Reinforcement Learning

no code implementations29 May 2018 Henrik Aslund, El Mahdi El Mhamdi, Rachid Guerraoui, Alexandre Maurer

We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adversary.

reinforcement-learning Reinforcement Learning (RL) +2

Asynchronous Byzantine Machine Learning (the case of SGD)

1 code implementation ICML 2018 Georgios Damaskinos, El Mahdi El Mhamdi, Rachid Guerraoui, Rhicheek Patra, Mahsa Taziki

The dampening component bounds the convergence rate by adjusting to stale information through a generic gradient weighting scheme.

BIG-bench Machine Learning

The Hidden Vulnerability of Distributed Learning in Byzantium

1 code implementation ICML 2018 El Mahdi El Mhamdi, Rachid Guerraoui, Sébastien Rouault

Based on this leeway, we build a simple attack, and experimentally show its strong to utmost effectivity on CIFAR-10 and MNIST.

Learning to Gather without Communication

1 code implementation21 Feb 2018 El Mahdi El Mhamdi, Rachid Guerraoui, Alexandre Maurer, Vladislav Tempez

A standard belief on emerging collective behavior is that it emerges from simple individual rules.

Multi-agent Reinforcement Learning Position

Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent

1 code implementation NeurIPS 2017 Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, Julien Stainer

We propose \emph{Krum}, an aggregation rule that satisfies our resilience property, which we argue is the first provably Byzantine-resilient algorithm for distributed SGD.

BIG-bench Machine Learning

On The Robustness of a Neural Network

no code implementations25 Jul 2017 El Mahdi El Mhamdi, Rachid Guerraoui, Sebastien Rouault

This bound involves dependencies on the network parameters that can be seen as being too pessimistic in the average case.

When Neurons Fail

no code implementations27 Jun 2017 El Mahdi El Mhamdi, Rachid Guerraoui

We view a neural network as a distributed system of which neurons can fail independently, and we evaluate its robustness in the absence of any (recovery) learning phase.

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

no code implementations NeurIPS 2017 El Mahdi El Mhamdi, Rachid Guerraoui, Hadrien Hendrikx, Alexandre Maurer

We give realistic sufficient conditions on the learning algorithm to enable dynamic safe interruptibility in the case of joint action learners, yet show that these conditions are not sufficient for independent learners.

Multi-agent Reinforcement Learning reinforcement-learning +1

Byzantine-Tolerant Machine Learning

no code implementations8 Mar 2017 Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, Julien Stainer

The growth of data, the need for scalability and the complexity of models used in modern machine learning calls for distributed implementations.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.